validate-idea
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates on untrusted data from user input and local files, creating a surface for indirect prompt injection attacks.
- Ingestion points: The skill ingests data from
$ARGUMENTS(the user's startup idea) and local filesfounder/facts.md,founder/product-brief.md, andfounder/competitor-matrix.md(SKILL.md). - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when interpolating this untrusted data into the agent's context.
- Capability inventory: The agent is authorized to use
WebSearchandWebFetchto look up competitors, andEdit(founder/**)to save the final validation report (SKILL.md). - Sanitization: There is no evidence of input validation or sanitization to prevent malicious instructions hidden in the startup idea or founder files from being executed by the agent.
Audit Metadata