validatekit
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from user-provided business idea files (e.g., IDEA.md, pitch drafts) and chat responses to perform its analysis. This content is used to generate premises and the final verdict.
- Ingestion points: The skill reads files specified in the invocation (Step 1) and user responses to forcing questions (Step 3).
- Boundary markers: Absent. There are no explicit instructions to the agent to treat these file contents as untrusted data or use delimiters.
- Capability inventory: Read, Write, Glob, WebSearch, and Agent (subagent spawning).
- Sanitization: Absent. The skill does not specify any sanitization or validation for the content of the business idea files.
Audit Metadata