ai-guardrail-coverage-auditor
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process structured input from external files, creating a surface for indirect prompt injection.
- Ingestion points:
run.pyreads untrusted data from a file path provided via the--inputcommand-line argument. - Boundary markers: There are no explicit markers or instructions to the model to ignore embedded commands within the processed data.
- Capability inventory: The skill possesses file system read and write capabilities through the
pathlibmodule inrun.py. - Sanitization: No sanitization, escaping, or schema validation is performed on the input content before it is processed.
Audit Metadata