offer-levers
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions and reference tables for business offer analysis. It does not perform network operations, file system modifications, or command execution.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted user-provided content (offer descriptions and pitch pages).
- Ingestion points: User-provided offer text, evidence, and objections.
- Boundary markers: None explicitly defined to separate user input from system instructions.
- Capability inventory: Limited to generating text-based scoring and improvement suggestions. No subprocess calls or external actions.
- Sanitization: No specific sanitization of input text is performed.
- While the skill processes external data, the lack of dangerous capabilities (network, file, or shell access) makes this a low-risk surface.
Audit Metadata