agentic-actions-auditor

Name: agentic-actions-auditor
Availability: InStock
Author: Ramprasad

Audit GitHub Actions workflows for AI agent security vulnerabilities.

1|Updated Feb 17, 2026

Search Tags:#github actions #ci/cd security #ai security #prompt injection #vulnerability analysis #agentic actions

Ready to run

npx skills add https://github.com/Ramprasad4121/srp --skill agentic-actions-auditor-ramprasad4121

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: agentic-actions-auditor
Source: https://github.com/Ramprasad4121/srp/tree/main/skills-repos/trailofbits/plugins/agentic-actions-auditor/skills/agentic-actions-auditor
Command: npx skills add https://github.com/Ramprasad4121/srp --skill agentic-actions-auditor-ramprasad4121

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

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.

Frequently Asked Questions about agentic-actions-auditor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I audit GitHub Actions workflows for AI agent prompt injection risks?▼

To audit GitHub Actions workflows for AI agent prompt injection risks, scan the workflow files to detect where attacker-controlled input reaches AI coding agents. This process identifies vulnerabilities like direct expression injection and dangerous sandbox configurations before unauthorized access occurs.

What security vulnerabilities affect AI coding agents like Claude Code Action and Gemini CLI in CI/CD pipelines?▼

Security vulnerabilities affecting AI coding agents in CI/CD pipelines include env var intermediary patterns, direct expression injection, dangerous sandbox configurations, and wildcard user allowlists. These attack vectors allow malicious input to manipulate AI agents running in GitHub Actions workflows.

How can I check if my GitHub Actions workflow exposes AI agents to unauthorized data access?▼

You can check if your GitHub Actions workflow exposes AI agents to unauthorized data access by auditing the pipeline for dangerous sandbox configurations and wildcard user allowlists. Analyzing workflow files reveals whether attacker-controlled input can reach AI integrations like OpenAI Codex.

Does this CI/CD security audit detect vulnerabilities in OpenAI Codex integrations?▼

Yes, this CI/CD security audit detects vulnerabilities in OpenAI Codex integrations. It locates specific AI agent integrations within workflow files and analyzes attack vectors where attacker-controlled input reaches the AI agent, preventing potential prompt injection attacks.

When should I run an agentic actions security audit on my repository?▼

You should run an agentic actions security audit on your repository when reviewing workflow files that invoke AI coding agents, auditing CI/CD pipeline security for prompt injection risks, or evaluating agentic action configurations to prevent unauthorized data access.

What is an env var intermediary pattern in GitHub Actions AI workflows?▼

An env var intermediary pattern in GitHub Actions AI workflows is an attack vector where environment variables pass attacker-controlled input to AI agents. Detecting this pattern during CI/CD pipeline security audits prevents prompt injection attacks targeting integrations like Claude Code Action.