asset-audit
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the asset directories and source code files which could potentially contain malicious instructions intended to manipulate the agent context.
- Ingestion points: Asset directories (assets/**/*), design documentation files, and project source code.
- Boundary markers: None identified; the instructions do not implement specific delimiters or 'ignore' directives for processed file content.
- Capability inventory: The skill is restricted to the Read, Glob, and Grep tools, providing no capability for data exfiltration or system modification.
- Sanitization: No validation, escaping, or sanitization of external asset content is performed before processing.
Audit Metadata