retro
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from session logs and repository configuration files, which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The agent reads local session logs and files such as package.json and AGENTS.md (SKILL.md, Steps 2 and 3).
- Boundary markers: The instructions lack explicit delimiters or safety markers to differentiate data from instructions during analysis.
- Capability inventory: The skill suggests environment modifications like pre-commit hooks and linting rules based on its analysis. However, the disable-model-invocation: true setting in the frontmatter provides significant protection by preventing the agent from autonomously executing tools.
- Sanitization: There are no instructions for sanitizing or escaping the content retrieved from logs before it is processed by the agent.
Audit Metadata