release-usage-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external structured data (JSON/CSV) as described in
SKILL.md. While the current implementation inrun.pyis a benign scaffold that only extracts object keys, the ingestion of external data constitutes a potential attack surface if future versions process natural language instructions embedded within the data. - Ingestion points: The skill reads input from a user-specified file path in
run.py. - Capability inventory: The script has file read/write capabilities but no network access or dynamic code execution.
- Boundary markers: None present in the current scaffold.
- Sanitization: Not applicable to the current implementation logic.
Audit Metadata