loop-me
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface by processing user input and writing the results to workspace files.
- Ingestion points: User responses during the
/grillinginteractive session defined inSKILL.md. - Boundary markers: The instructions do not define specific delimiters to separate untrusted user input from the generated file content.
- Capability inventory: The skill possesses the ability to create, modify, and delete files within the
workflows/directory and updateNOTES.md. - Sanitization: There is no evidence of explicit sanitization, filtering, or validation of user-provided content before it is written to the file system.
Audit Metadata