deal-review-framework
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied sales deal information to generate reviews, creating an attack surface where malicious data could influence agent behavior.
- Ingestion points: User data enters via deal review requests described in the "Common Use Cases" section of
SKILL.md. - Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded within the deal data.
- Capability inventory: The skill is limited to generating formatted text outputs; no subprocess calls, file-system writes, or network operations were found in the instructions.
- Sanitization: There are no explicit instructions for the agent to sanitize or escape input before interpolation into the output template.
Audit Metadata