meta-due-diligence
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, including business plans, supporting documents, and OSINT search results.
- Ingestion points:
SKILL.md(Required Inputs section) andreferences/osint-business-intelligence.md(OSINT investigation layers). - Boundary markers: The instructions emphasize verification and cross-referencing but do not define specific prompt delimiters for untrusted input.
- Capability inventory: The skill is purely instructional markdown and does not include any scripts, automated tool execution, or network capabilities.
- Sanitization: No sanitization or escaping of external content is mentioned.
Audit Metadata