loop-me
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of instructional markdown and configuration YAML. There are no scripts, executables, or code files included.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided input and data from NOTES.md to generate workflow specifications. 1. Ingestion points: User input and the NOTES.md file are the primary sources of data. 2. Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the source data. 3. Capability inventory: The skill is restricted to file operations (creating, editing, deleting) within the workflows directory and NOTES.md. It has no network or shell execution capabilities. 4. Sanitization: No explicit sanitization or validation of the input data is performed before interpolation into the output specifications.
Audit Metadata