agentic-actions-auditor
CommunitySecure AI agent integrations in GitHub Actions.
Software Engineering#github actions#ci/cd security#ai security#prompt injection#vulnerability analysis#agentic actions
AuthorRamprasad4121
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill identifies and analyzes security vulnerabilities within GitHub Actions workflows that integrate with AI coding agents, preventing potential prompt injection attacks and unauthorized access.
Core Features & Use Cases
- AI Action Discovery: Locates specific AI agent integrations like Claude Code Action, Gemini CLI, and OpenAI Codex within workflow files.
- Attack Vector Analysis: Detects common vulnerabilities such as env var intermediaries, direct expression injection, dangerous sandbox configurations, and wildcard user allowlists.
- Use Case: When auditing a repository's CI/CD pipeline, use this Skill to ensure that AI agents invoked in GitHub Actions workflows are not susceptible to prompt injection or unauthorized data access.
Quick Start
Use the agentic-actions-auditor skill to audit the GitHub Actions workflows in the current repository for AI agent security risks.
Dependency Matrix
Required Modules
None requiredComponents
references
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: agentic-actions-auditor Download link: https://github.com/Ramprasad4121/srp/archive/main.zip#agentic-actions-auditor Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.