link-building
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data which could contain adversarial instructions.
- Ingestion points: Reads marketing context from local files (e.g., .agents/product-marketing.md) and fetches external data using tools like Firecrawl and Exa (SKILL.md).
- Boundary markers: Lacks explicit delimiters or instructions to ignore embedded commands in external data.
- Capability inventory: Uses search tools and generates outreach emails for user review (SKILL.md, references/tactics.md).
- Sanitization: No formal sanitization of ingested content is mentioned, relying on human review of final drafts.
Audit Metadata