governance-policy-gap-finder
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process structured input data (JSON or CSV), which creates a potential surface for indirect prompt injection if the processed data contains malicious instructions for the AI agent.\n
- Ingestion points: The script
run.pyreads data from a file path provided via the--inputargument usinginput_path.read_text().\n - Boundary markers: The current implementation does not include boundary markers or explicit instructions to the agent to ignore instructions embedded within the data.\n
- Capability inventory: The skill has the capability to read files, create directories, and write files to the local file system through
run.py.\n - Sanitization: No data validation or sanitization is performed on the input payload beyond standard JSON parsing.
Audit Metadata