repo-audit
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands and uses a Python script (scripts/collect_evidence.py) to invoke the gh (GitHub CLI) and git tools to retrieve repository information. The script uses the standard library and list-based subprocess calls to interact with these tools safely.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it processes untrusted content from the repository being audited (e.g., README files, metadata). * Ingestion points: Repository metadata and file contents are read via the gh API and filesystem in scripts/collect_evidence.py. * Boundary markers: The skill uses a structured checklist (references/audit-checklist.md) but lacks explicit delimiters or instructions to ignore embedded commands within the audited data. * Capability inventory: The skill has the ability to execute CLI tools and read/write files in the local environment. * Sanitization: No filtering or sanitization is performed on the ingested repository content before it is analyzed by the agent.
Audit Metadata