improve-search-visibility-question-set
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data that could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill reads Search Console exports, customer language banks from research/audience/voc-bank.md, and utilizes the gooseworks:knowledge_search tool to fetch customer objections and questions.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the ingested data as untrusted or to ignore any embedded commands.
- Capability inventory: The skill is authorized to write to the file system (search/questions.md) and use a suite of gooseworks-branded analysis tools.
- Sanitization: No evidence of data validation or sanitization is present in the instructions for processing external content.
Audit Metadata