guidance-tracker
Pass
Audited by Gen Agent Trust Hub on Aug 2, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests untrusted data from SEC filings, company transcripts, and web search results. The risk is mitigated by strict source quality requirements that mandate primary sources and forbid data from high-risk aggregators or blog sites. Boundary markers for data access are defined in the referenced data-access.md file.
- [COMMAND_EXECUTION]: The skill performs file system operations by generating and saving a structured HTML report to the 'reports/' directory. This behavior is consistent with the skill's primary purpose of data analysis and reporting.
Audit Metadata