product-usage-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted structured data from external sources.
- Ingestion points: The
run.pyscript reads JSON data from a path specified by the--inputcommand-line argument. - Boundary markers: The skill instructions do not define delimiters or specific isolation markers to distinguish between data and potential instructions embedded within the input files.
- Capability inventory: The skill performs file system operations including reading files (
Path.read_text), creating directories (Path.mkdir), and writing files (Path.write_text) in therun.pyscript. - Sanitization: No input validation, escaping, or sanitization logic is implemented in the reference scaffold before the payload keys are processed and summarized.
Audit Metadata