value-prop-builder
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns detected. The skill's behavior is consistent with its stated purpose of facilitating marketing strategy.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes external and local untrusted data.
- Ingestion points: Reads from 'pmf/icp.md' and results from 'WebSearch'.
- Boundary markers: No delimiters or safety instructions are used to wrap untrusted content.
- Capability inventory: Uses 'Read', 'Write', 'Glob', and 'WebSearch' tools.
- Sanitization: No sanitization or validation of ingested data is performed.
Audit Metadata