jurisdiction-format
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided patent documents, which could contain hidden instructions targeting the agent.
- Ingestion points: Reads content from files in the
patent/directory, includingCLAIMS.mdand specification sections. - Boundary markers: No delimiters or instructions are used to separate user data from the agent's logic or to warn the agent about embedded instructions.
- Capability inventory: The skill uses
Bash(*),Read,Write, andEdittools to generate and modify files. - Sanitization: There is no filtering or validation of the input text content before it is processed or written to output files.
Audit Metadata