general-counsel-advisor
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted legal documents, which serves as a potential vector for indirect prompt injection.
- Ingestion points: The scripts
contract_risk_scanner.pyandterm_sheet_analyzer.pyread external files (contracts in text format and term sheets in JSON format) into the agent's context. - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" wrappers to isolate the untrusted document content from the agent's core instructions.
- Capability inventory: While the provided scripts use standard libraries for analysis, the agent's broader capabilities (file system access and logic execution) could be manipulated if it follows instructions embedded within the analyzed legal text.
- Sanitization: No specific sanitization or filtering logic is present in the scripts to detect or neutralize natural language instructions hidden within the document data before it is processed by the agent.
Audit Metadata