command-research
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external market research, competitor data, and keyword evidence, which could potentially contain malicious instructions intended to influence the agent's behavior during summarization or file writing.
- Ingestion points: External evidence collected from market, competitor, and keyword sources (SKILL.md, Step 2 and 3).
- Boundary markers: The instructions do not define specific delimiters or instructions to treat the collected research data as untrusted content.
- Capability inventory: The skill utilizes file system writing capabilities to persist collected findings to the
research/directory (SKILL.md, Step 5). - Sanitization: There is no evidence of sanitization, filtering, or validation of the external content before it is processed and written to the file system.
Audit Metadata