loop-me
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No high-risk behaviors detected. The skill is designed to function as a documentation assistant, managing workflow specifications in the local workspace without network access, external downloads, or code execution capabilities.
- [PROMPT_INJECTION]: Potential surface for indirect prompt injection as the skill processes user-provided content from notes to generate specifications.
- Ingestion points: NOTES.md and interactive user input dialogue.
- Boundary markers: None present; the skill does not use specific delimiters to separate untrusted data from instructions.
- Capability inventory: File read and write access restricted to workflows/*.md and NOTES.md. No sensitive file access or command execution tools are used.
- Sanitization: None detected; input content is processed and recorded without explicit validation or escaping.
Audit Metadata