loop-me
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information and notes to generate workflow documentation, presenting an inherent surface for indirect instruction processing.
- Ingestion points: The skill reads from NOTES.md and processes interactive user responses.
- Boundary markers: No explicit delimiters or boundary markers for external data are specified in the instructions.
- Capability inventory: The skill specifies the ability to create, edit, and delete markdown files in the workflows/ directory and the NOTES.md file.
- Sanitization: No specific sanitization or validation rules for ingested note content are defined in the instructions.
Audit Metadata