business-idea-validator
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingest untrusted user data and investigates external content from the web, creating a surface for indirect prompt injection.
- Ingestion points: SKILL.md (processes user prose, ideas, founder context, and user-supplied links/documents).
- Boundary markers: Absent; the instructions do not use delimiters or isolation rules to separate user-supplied content from agent instructions.
- Capability inventory: The agent is authorized to perform web research and inspect user-provided URLs and documents to gather evidence.
- Sanitization: Absent; there are no instructions to sanitize, escape, or filter instructions that might be embedded in the processed external data.
Audit Metadata