Search Results for "command-injection" | AgentCC

proton-pass

Manage Proton Pass vaults, items (logins, SSH keys, aliases, notes), passwords, SSH agent integration, and secret injection into applications. Use when working with Proton Pass for password management, SSH key storage, secret injection (run commands with secrets, inject into templates), environment variable injection, or generating secure passwords. Supports vault/item CRUD, sharing, member management, SSH agent operations, TOTP generation, secret references (pass://vault/item/field), template injection, and command execution with secrets.

openclaw-sec

Openclaw Skills Openclaw Sec

AI Agent Security Suite - Real-time protection against prompt injection, command injection, SSRF, path traversal, secrets exposure, and content policy violations

clawdefender

Security scanner and input sanitizer for AI agents. Detects prompt injection, command injection, SSRF, credential exfiltration, and path traversal attacks. Use when (1) installing new skills from ClawHub, (2) processing external input like emails, calendar events, Trello cards, or API responses, (3) validating URLs before fetching, (4) running security audits on your workspace. Protects agents from malicious content in untrusted data sources.

scanning-input-validation-practices

jeremylongshore

This skill enables Claude to automatically scan source code for potential input validation vulnerabilities. It identifies areas where user-supplied data is not properly sanitized or validated before being used in operations, which could lead to security exploits like SQL injection, cross-site scripting (XSS), or command injection. Use this skill when the user asks to "scan for input validation issues", "check input sanitization", "find potential XSS vulnerabilities", or similar requests related to securing user input. It is particularly useful during code reviews, security audits, and when hardening applications against common web vulnerabilities. The skill leverages the input-validation-scanner plugin to perform the analysis.

vuln-analysis-expert

WooYun Vulnerability Analysis Expert System. A meta-thinking methodology, testing processes, exploitation techniques, and bypass methods distilled from 88,636 real vulnerability cases. It covers major vulnerability types such as SQL injection, XSS, command execution, logic flaws, file uploads, unauthorized access, etc. Triggered when users conduct vulnerability mining, penetration testing, security audits, and code audits.

command-injection-testing

Professional skills and methodology for command injection testing

octocode-prompt-optimizer

This skill should be used when the user asks to "optimize this prompt", "improve this SKILL.md", "make this prompt more reliable", "fix my agent instructions", "review this AGENTS.md", "strengthen this prompt", "my agent keeps skipping steps", "add enforcement to instructions", or needs to transform weak prompts into reliable, enforceable agent protocols. Uses a 6-step gated flow (with Fast/Full modes), command strengthening, gate injection, and failure mode analysis.

command-injection-testing

Anshumanbh Securevibes Command Injection Testing

Validate OS Command Injection vulnerabilities including direct command injection, blind command injection via time delays, and out-of-band command execution. Test by injecting shell metacharacters and commands into user-controlled inputs. Use when testing CWE-78 (OS Command Injection), CWE-77 (Command Injection), CWE-88 (Argument Injection), or related command execution vulnerabilities.

input-validation

Implement comprehensive input validation to prevent XSS, SQL injection, and command injection attacks with sanitization strategies

security-bun

Review Bun runtime security audit patterns. Use for auditing Bun-specific vulnerabilities including shell injection, SQL injection, server security, and process spawning. Use proactively when reviewing Bun apps (bun.lockb, bunfig.toml, or bun:* imports present). Examples: - user: "Review this Bun shell script" → audit `$` usage and argument injection - user: "Check my bun:sqlite queries" → verify `sql` tagged template usage - user: "Audit my Bun.serve() setup" → check path traversal and request limits - user: "Is my Bun.spawn() usage safe?" → audit command injection and input validation - user: "Review WebSocket security in Bun" → check authentication before upgrade

cli-module

myfy CliModule for custom CLI commands with DI injection. Use when working with CliModule, @cli.command decorator, command groups, CLI arguments, CLI options, or myfy app commands.

rails-ai:security

Zerobearing2 Rails Ai Security

CRITICAL - Use when securing Rails applications - XSS, SQL injection, CSRF, file uploads, command injection prevention

code-review

Review code for quality, security, and best practices. Analyze pull requests, identify bugs, suggest improvements, verify error handling, check for security vulnerabilities (XSS, SQL injection, command injection), evaluate design patterns, and assess performance. Use when reviewing pull requests, examining code diffs, evaluating code changes, or analyzing implementation quality.

input-validation-sanitization-auditor

patricio0312rev

Identifies and fixes XSS, SQL injection, and command injection vulnerabilities with validation schemas, sanitization libraries, and safe coding patterns. Use for "input validation", "XSS prevention", "SQL injection", or "sanitization".

Symfony

Comprehensive skill for all Symfony framework components. Covers HTTP handling, dependency injection, forms, validation, caching, messaging, console commands, event dispatching, workflows, serialization, testing, filesystem operations, configuration, and utility components. Use when working with any Symfony component.

FastAPI

FastAPI modern Python web framework. Use for building APIs, async endpoints, dependency injection, and Python backend development.

security-checker

Security checking capability that runs while editing code. Automatically activates when a user edits files, modifies code, or performs a code review. Monitors for command injection, XSS, eval usage, credential exposure, unsafe postMessage patterns, and other security risks. Inspired by Anthropic's official security-guidance plugin.

security-bun

justinlevinedotme

Review Bun runtime security audit patterns. Use for auditing Bun-specific vulnerabilities including shell injection, SQL injection, server security, and process spawning. Use proactively when reviewing Bun apps (bun.lockb, bunfig.toml, or bun:* imports present). Examples: - user: "Review this Bun shell script" → audit `$` usage and argument injection - user: "Check my bun:sqlite queries" → verify `sql` tagged template usage - user: "Audit my Bun.serve() setup" → check path traversal and request limits - user: "Is my Bun.spawn() usage safe?" → audit command injection and input validation - user: "Review WebSocket security in Bun" → check authentication before upgrade

Global Validation

Implement secure, comprehensive input validation on both client and server sides using allowlists, type checking, and sanitization to prevent injection attacks. Use this skill when handling user input from forms, API requests, or any external data source. When implementing form validation logic with field-specific error messages. When validating data types, formats, ranges, and required fields. When sanitizing input to prevent SQL injection, XSS, or command injection. When validating business rules like sufficient balance or valid date ranges. When implementing both client-side validation for user experience and mandatory server-side validation for security.

testing-web-applications

Test web applications for security vulnerabilities including SQLi, XSS, command injection, JWT attacks, SSRF, file uploads, XXE, and API flaws. Use when pentesting web apps, analyzing authentication, or exploiting OWASP Top 10 vulnerabilities.

vibe-security

Security intelligence for code analysis. Detects SQL injection, XSS, CSRF, authentication issues, crypto failures, and more. Actions: scan, analyze, fix, audit, check, review, secure, validate, sanitize, protect. Languages: JavaScript, TypeScript, Python, PHP, Java, Go, Ruby. Frameworks: Express, Django, Flask, Laravel, Spring, Rails. Vulnerabilities: SQL injection, XSS, CSRF, authentication bypass, authorization issues, command injection, path traversal, insecure deserialization, weak crypto, sensitive data exposure. Topics: input validation, output encoding, parameterized queries, password hashing, session management, CORS, CSP, security headers, rate limiting, dependency scanning.

pentest-injection-engine

Systematically test authorized targets for SQL, XSS, SSTI, XXE, command, and request-smuggling injection classes.

detecting-attacks-on-scada-systems

This skill covers detecting cyber attacks targeting Supervisory Control and Data Acquisition (SCADA) systems including man-in-the-middle attacks on industrial protocols, unauthorized command injection into PLCs, HMI compromise, historian data manipulation, and denial-of-service against control system communications. It leverages OT-specific intrusion detection systems, industrial protocol anomaly detection, and process data analytics to identify attacks that traditional IT security tools miss.

ot-securityicsscada+4

exploiting-api-injection-vulnerabilities

Tests APIs for injection vulnerabilities including SQL injection, NoSQL injection, OS command injection, LDAP injection, and Server-Side Request Forgery (SSRF) through API parameters, headers, and request bodies. The tester crafts malicious payloads targeting different backend technologies and injection contexts to extract data, execute commands, or access internal services. Maps to OWASP API8:2023 Security Misconfiguration and API7:2023 SSRF. Activates for requests involving API injection testing, SQLi in APIs, NoSQL injection, SSRF testing, or API input validation assessment.

api-securityowaspinjection+4

detecting-modbus-command-injection-attacks

Detect command injection attacks against Modbus TCP/RTU protocol in ICS environments by monitoring for unauthorized write operations, anomalous function codes, malformed frames, and deviations from established communication baselines using ICS-aware IDS and protocol deep packet inspection.

ot-securityicsmodbus+5

fuzzing-apis

This skill enables Claude to perform automated fuzz testing on APIs to discover vulnerabilities, crashes, and unexpected behavior. It leverages malformed inputs, boundary values, and random payloads to generate comprehensive fuzz test suites. Use this skill when you need to identify potential SQL injection, XSS, command injection vulnerabilities, input validation failures, and edge cases in APIs. Trigger this skill by requesting fuzz testing, vulnerability scanning, or security analysis of an API. The skill is invoked using the `/fuzz-api` command.

security-agent

Security Engineer sub-agent. Scans code for OWASP Top 10 vulnerabilities, detects hardcoded secrets and API keys, reviews authentication and authorization implementations, identifies injection vectors (SQL, NoSQL, command, LDAP), checks for insecure dependencies, and performs threat modeling. Rates findings by CVSS severity. Use when auditing security, reviewing auth code, checking dependencies for CVEs, or before any production deployment. Triggers - security audit, vulnerability, OWASP, CVE, auth review, is this safe, security check, injection.

security-review

Code security review covering OWASP Top 10, injection prevention (SQL, XSS, command injection), authentication and authorization patterns, secrets management, dependency vulnerability scanning, input validation, CORS, CSRF, rate limiting, and security headers. Language-agnostic with examples in JavaScript, Python, and Go. Use when reviewing code for security or hardening an application.

audit-skill

Security audit for agent skills using a three-layer deterministic architecture: structural validation, instruction scanning (prompt injection, encoding tricks, exfiltration, overreach), and code analysis (secrets, dangerous patterns, semgrep SAST, trifecta detection). Produces a trust score (A-F) with per-layer breakdown. Use when reviewing a skill for security, auditing a skill before installation, checking for prompt injection, or when the user says 'audit skill', 'check skill security', 'trust score', 'is this skill safe', or 'audit-skill'. On-demand via /audit-skill command.

moltguard

MoltGuard — runtime security plugin for OpenClaw agents by OpenGuardrails. Helps users install, register, activate, and check the status of MoltGuard. Use when the user asks to: install MoltGuard, check MoltGuard status, register or activate MoltGuard, configure the AI Security Gateway, or understand what MoltGuard detects. Provides local-first protection against data exfiltration, credential theft, command injection, and sensitive data leakage. Source: https://github.com/openguardrails/openguardrails/tree/main/moltguard

API Pentest

Targeted API penetration testing using a GTFO-first approach: find the highest-impact vulnerability fast, prove it with a PoC, and move on. Covers five attack families: AuthN/AuthZ, BOLA/IDOR, Input Validation, SSRF, and Business Logic. Each family is a loadable module with specific test cases, payloads, and PoC templates. Trigger when user mentions "API pentest", "API security test", "test this API", "find vulnerabilities in this endpoint", "BOLA", "IDOR", "broken auth", "injection test", "SSRF", "business logic flaw", "API attack", or shares API docs, Swagger/OpenAPI specs, Postman collections, or curl commands.

remediation

Helps fix security vulnerabilities identified by DryRunSecurity. Activates when the user shares a DryRunSecurity comment (from a GitHub PR or GitLab MR) or asks for help fixing any security finding including SQL injection, XSS, CSRF, SSRF, path traversal, command injection, authentication bypass, authorization flaws, and prompt injection. Researches authoritative sources and applies fixes grounded in the user's specific codebase context.

openclaw-sec

BJS-Innovation-Lab

AI Agent Security Suite - Real-time protection against prompt injection, command injection, SSRF, path traversal, secrets exposure, and content policy violations

sql-injection-prevention

Prevents SQL injection attacks by enforcing parameterized queries and ORM patterns that keep user data separate from SQL commands. Triggers on: SQL query, database query, user input in query, dynamic query, string concatenation in SQL, f-string SQL, format SQL, raw SQL, execute query, %s in SQL, LIKE clause, ORDER BY, search.

command-creator

Create custom commands for Pi (prompt templates) or OpenCode. Define command prompts, arguments, shell output injection, file references, and configure agents, models, and descriptions.

gcp-injection

Use this skill when users need to audit, detect, or remediate Injection vulnerabilities (OWASP A03:2021) on Google Cloud Platform. This includes SQL injection, Cross-Site Scripting (XSS), command injection, LDAP injection, and any scenario where untrusted data is sent to an interpreter. Covers configuring Cloud Armor WAF preconfigured rule sets (sqli-stable, xss-stable, rce-stable, php-stable), reviewing Security Command Center findings for injection-related threats (Container Threat Detection, Web Security Scanner), and auditing Apigee API proxies for JSON/XML threat protection. Activate for GCP WAF hardening, injection prevention, or OWASP A03 compliance.

prompt-injection-security

Detection and prevention of prompt injection attacks in AI agent/skill/command systems. Use when authoring, reviewing, or ingesting markdown artifacts that will be loaded as LLM context.

Prompt Guard

Advanced prompt injection defense system for Clawdbot. Protects against direct and indirect injection attacks in group chats with multi-language detection (English, Korean, Japanese, Chinese), severity scoring, automatic logging, and configurable security policies. Use in any group context to restrict sensitive commands to the owner and detect manipulation attempts.

claude

Full-surface security governance for Claude Code. Use when scanning CLAUDE.md or AGENTS.md for injection, reviewing hooks for unsafe commands, auditing slash commands or memory files, enforcing sub-agent budget limits, checking settings drift, or handling any Claude Code governance decision code.