asset-license-checker
Pass
Audited by Gen Agent Trust Hub on Nov 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted asset metadata, including names and source URLs, which serves as an injection surface.
- Ingestion points: Ingests
candidate_assets(name, source URL, license label) as defined incontract.jsonand the Operating Procedure inSKILL.md. - Boundary markers: Absent; there are no explicit delimiters or instructions to the agent to disregard instructions embedded within the asset data.
- Capability inventory: None; the skill explicitly disclaims the use of Python, Blender, or any arbitrary interfaces, and contains no code for subprocess execution, file modification, or network operations.
- Sanitization: Absent.
- [SAFE]: No signs of prompt injection, obfuscation, data exfiltration, or persistence mechanisms were found. The skill operates as a static validation gate based on documented reference rules.
Audit Metadata