funding-signal-outreach
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data which introduces a surface for indirect prompt injection.
- Ingestion points: Funding announcements retrieved via web search in Step 1 and company lists imported from CSV or CRM sources in Step 0.
- Boundary markers: No delimiters or instructions are used to separate ingested data from agent instructions.
- Capability inventory: The skill utilizes web-search, file system writing for configuration and output, and integration with external outreach platforms.
- Sanitization: There are no defined processes for sanitizing or validating external input before it is interpolated into prompts for lead qualification and email drafting.
Audit Metadata