figure-description
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external files which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Processes
patent/INVENTION_DISCLOSURE.md,patent/CLAIMS.md, and various image files (PNG, JPG, SVG, PDF) discovered in the project directory using the Glob and Read tools. - Boundary markers: Lacks explicit delimiters or instructions to ignore embedded prompts within the processed patent documentation.
- Capability inventory: The skill is configured with broad tool access including
Bash(*),Write,Edit,WebSearch, andWebFetch. - Sanitization: No validation or sanitization steps are defined for the content extracted from the external documents before they are used to generate outputs or mapping indexes.
Audit Metadata