agentic actions auditor

DevOps Community

Skill notes

When to Use

Auditing a repository's GitHub Actions workflows for AI agent security Reviewing CI/CD configurations that invoke Claude Code Action, Gemini CLI, or OpenAI Codex Checking whether attacker-controlled input can reach AI agent prompts Evaluating agentic action configurations (sandbox settings, tool permissions, user allowlists) Assessing trigger events that expose workflows to external input (pull_request_target, issue_comment, etc.)

When NOT to Use

Analyzing workflows that do NOT use any AI agent actions (use general Actions security tools instead) Reviewing standalone composite actions or reusable workflows outside of a caller workflow context (use this skill when analyzing a workflow that references them via uses:) Performing runtime prompt injection testing (this is static analysis guidance, not exploitation) Auditing non-GitHub CI/CD systems (Jenkins, GitLab CI, CircleCI)

Rationalizations to Reject

When auditing agentic actions, reject these common rationalizations. Each represents a reasoning shortcut that leads to missed findings. 1. "It only runs on PRs from maintainers" Wrong because it ignores pull_request_target, issue_comment, and other trigger events that expose actions to external input. Attackers do not need write access to trigger these workflows. A pull_request_target event runs in the context of the base branch, not the PR branch, meaning any external contributor can trigger it by opening a PR.

Audit Methodology

Follow these steps in order. Each step builds on the previous one.

Step 0: Determine Analysis Mode

If the user provides a GitHub repository URL or owner/repo identifier, use remote analysis mode. Otherwise, use local analysis mode (proceed to Step 1). URL Parsing Extract owner/repo and optional ref from the user's input: Input Format · Extract owner/repo · owner, repo; ref = default branch

Fluxly profile Runtime and permissions are inferred by Fluxly static checks, not author declarations or runtime test results.
Domain
DevOps
Author-declared agents
No explicit declaration found; this is not inferred or tested compatibility
Static check
88 / 100 · heuristic scan, not runtime safety proof
Runtime evidence
Not run; no isolated runtime test evidence is currently recorded
Author / version / license
@open-edge-platform · no license declared
Token usage
Heavy
Setup complexity
Manual integration
External API key
Required · GitHub
Operating systems
macOS · Linux · Windows
Runtime requirements
Node.js · Python
Detected file/system behavior
  • Read-only
  • Write / modify
  • Shell exec
  • Env read
Network behavior
External requests
Install commands
None (reference only)

Heads up: Tool permissions are not declared; actual access depends on the runtime.

01
Step 0: Determine Analysis Mode

If the user provides a GitHub repository URL or `owner/repo` identifier, use remote analysis mode. Otherwise, use local analysis mode (proceed to Step 1). URL Parsing Extract `owner/repo` and optional `ref` from the user's input: Input Format · Extract `owner/repo` · owner, repo; ref = default branch

02
Step 1: Discover Workflow Files

Use Glob to locate all GitHub Actions workflow files in the repository. Search for workflow files: Glob for `.github/workflows/*.yml` Glob for `.github/workflows/*.yaml` If no workflow files are found, report "No workflow files found" and stop the audit

03
Step 2: Identify AI Action Steps

For each workflow file, examine every job and every step within each job. Check each step's `uses:` field against the known AI action references below. Known AI Action References: Action Reference · Action Type `anthropics/claude-code-action` · Claude Code Action `google-github-actions/run-gemini-cli` · Gemini CLI

04
Step 3: Capture Security Context

For each identified AI action step, capture the following security-relevant information. This data is the foundation for attack vector detection in Step 4. 3a. Step-Level Configuration (from `with:` block) Capture these security-relevant input fields based on the action type: Claude Code Action: `prompt` -- the instruction sent to the AI agent

05
Step 4: Analyze for Attack Vectors

First, read references/foundations.md to understand the attacker-controlled input model, env block mechanics, and data flow paths. Then check each vector against the security context captured in Step 3: Vector · Name · Quick Check · Reference A · Env Var Intermediary · `env:` block with `${{ github.event.* }}` value + prompt reads that env var name · references/vector-a-env-var-intermediary.md B · Direct Expression Injection · `${{ github.event.* }}` inside prompt or system-prompt field · references/vector-b-direct-expression-injection.md

06
Step 5: Report Findings

Transform the detections from Step 4 into a structured findings report. The report must be actionable -- security teams should be able to understand and remediate each finding without consulting external documentation. 5a. Finding Structure Each finding uses this section order: Title: Use the vector name as a heading (e.g., `### Env Var Intermediary`). Do not prefix with vector letters. Severity: High / Medium / Low / Info (see 5b for judgment guidance)

Discussion

Powered by GitHub Discussions. Sign in with GitHub to comment, react, or subscribe.