woocommerce-stale-pr-audit
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the execution of local scripts and the GitHub CLI (gh) to perform its core functions. It executes scripts like collect_cohort.py and fetch_live_state.mjs to retrieve repository data and validate audit results.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted pull request data that may contain malicious instructions.
- Ingestion points: The scripts/collect_cohort.py script fetches pull request content, including titles, bodies, and comments, directly from the GitHub API and incorporates them into the agent's context for analysis.
- Boundary markers: The instructions do not specify the use of clear delimiters or instructions to ignore embedded commands within the pull request content being audited.
- Capability inventory: The agent has capabilities including local shell command execution via subprocess and execFileSync, file system access for writing reports, and instructions to perform runnable user testing using browser or CLI tools.
- Sanitization: There is no evidence of explicit sanitization or filtering of the external pull request content before it is interpolated into prompts or used in the audit workflow.
Audit Metadata