billing-access-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input data, which constitutes a potential injection surface.\n- Ingestion points: The
run.pyscript reads files from the path specified in the--inputargument.\n- Boundary markers: No boundary markers or delimiters are used to isolate untrusted content.\n- Capability inventory: The skill has file system read and write capabilities via thepathlibmodule inrun.py.\n- Sanitization: The input content is loaded and processed as JSON without additional sanitization or validation.
Audit Metadata