sponsored-newsletter-finder
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the web, creating a surface for indirect prompt injection attacks.
- Ingestion points: The skill relies on results from the
web_searchtool (Phase 1 and 2) to find and evaluate newsletters from external platforms like Substack, Beehiiv, and various directories. - Boundary markers: The instructions lack explicit boundary markers (e.g., XML tags or clear delimiters) or warnings telling the agent to ignore instructions potentially embedded in the retrieved web content.
- Capability inventory: The skill includes instructions to write the final research report to the local file system at paths like
clients/<client-name>/intelligence/newsletter-sponsors-[YYYY-MM-DD].md. - Sanitization: There is no evidence of sanitization, filtering, or validation of the external content before it is scoring and interpolated into the final markdown report.
Audit Metadata