data-catalog-coverage-auditor
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external structured data (JSON/CSV), which serves as a vector for indirect prompt injection if the data source is untrusted.
- Ingestion points: The
run.pyscript reads the content of a file provided via the--inputcommand-line argument usingPath.read_text()andjson.loads(). - Boundary markers: There are no specific delimiters or instructions provided in
SKILL.mdto guide the agent on how to handle or ignore potentially malicious instructions embedded within the data. - Capability inventory: The
run.pyscript performs local filesystem read and write operations (read_text,write_text,mkdir). - Sanitization: The input payload is processed without validation or sanitization, though the current implementation only extracts keys.
Audit Metadata