funding-signal-outreach
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates on untrusted external data which could potentially contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Data is ingested from external company lists (Step 0), web search results for funding announcements (Step 1), and contact discovery tools (Step 3).
- Boundary markers: The instructions do not define specific delimiters or "ignore instructions" prompts when processing this external data in Step 2 (Qualification) or Step 4 (Email Drafting).
- Capability inventory: The skill utilizes network tools for searches and API calls (Step 1, Step 3, Step 5) and performs file writing for configuration and campaign exports (Step 0, Step 5).
- Sanitization: There is no evidence of sanitization or validation logic for external data before it is interpolated into LLM prompts for reasoning tasks.
Audit Metadata