security-migration-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external structured data (JSON/CSV), which serves as an ingestion point for untrusted content. While the current implementation is a scaffold, processing untrusted data is a known attack surface.
- Ingestion points: The script
run.pyreads data from a file path provided via the--inputcommand-line argument. - Boundary markers: None present; data is loaded directly via
json.loadswithout explicit isolation instructions. - Capability inventory: The skill has filesystem write access through the
--outputargument andPath.write_textinrun.py. - Sanitization: Input data is not sanitized or validated beyond standard JSON parsing.
Audit Metadata