prospecting
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies buying triggers by instructing the agent to ingest and analyze untrusted external data sources, including job postings, public security incident reports, and technical migration signals from repositories.
- Ingestion points: External web content from job boards, news sites, and public code repositories mentioned in Step 2 and routing evaluations.
- Boundary markers: The instructions do not define delimiters or provide specific instructions to the agent to ignore commands that may be embedded within the processed data.
- Capability inventory: The skill is intended for use with tools capable of performing web searches, fetching remote content, and writing detailed prospecting reports to the local filesystem (PROSPECTING-LIST.md).
- Sanitization: No sanitization or validation mechanisms are mentioned for the data fetched from these external sources.
Audit Metadata