regulatory-compliance
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface detected.\n
- Ingestion points: Untrusted content is ingested from files specified by the
dpaPathparameter during agreement validation.\n - Boundary markers: The skill does not implement delimiters or instructions to ignore embedded commands in the processed documents.\n
- Capability inventory: The agent has access to
Read,Write,Glob, andGreptools and executes local scripts.\n - Sanitization: No sanitization or validation is applied to the content of ingested files before they are processed by the agent.\n- [COMMAND_EXECUTION]: Execution of local scripts and hooks.\n
- Evidence: The skill executes
scripts/main.cjsto generate report templates.\n - Evidence: Pre- and post-execution hooks (
hooks/pre-execute.cjs,hooks/post-execute.cjs) are utilized for validation and observability, involving the dynamic loading of local modules.
Audit Metadata