deal-review-framework
Pass
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: LOWNO_CODE
Full Analysis
- SAFE (SAFE): No malicious patterns, obfuscation, or sensitive data access were identified. The skill acts purely as a prompt template for sales methodology coaching.
- NO_CODE (INFO): The skill is entirely text-based and does not include any scripts, binaries, or package dependencies, which minimizes the technical attack surface.
- PROMPT_INJECTION (INFO): While the skill uses instructional framing for a specific persona, it does not contain markers for overriding system instructions or bypassing safety filters.
- INDIRECT_PROMPT_INJECTION (INFO): The skill processes user-supplied deal information for coaching purposes. 1. Ingestion points: User-provided deal details in prompt requests. 2. Boundary markers: Absent. 3. Capability inventory: Limited to generating formatted Markdown text output. 4. Sanitization: Absent. Risk is classified as INFO because the skill has no side-effect capabilities like file writing or network access.
Audit Metadata