kero-research
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and synthesize untrusted data from external sources including store listings, public filings, and user reviews to produce a thesis.
- Ingestion points: Product pages, competitor sites, and user review sections accessed during the research process as specified in the body of SKILL.md.
- Boundary markers: The skill provides instructions to link every claim to a verifiable source and clearly label opinions, which helps the agent distinguish between objective data and subjective claims.
- Capability inventory: The skill's primary capability is writing the final diagnosis to a local document at
docs/research.md. - Sanitization: There are no explicit instructions for the agent to sanitize or ignore instructions potentially embedded within the third-party research data.
- [SAFE]: No malicious patterns such as command execution, credential harvesting, or persistence mechanisms were detected. The skill follows standard research best practices and limits its operations to information gathering and documentation.
Audit Metadata