life-open-learning-track
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill consists entirely of markdown instructions and a JSON evaluation file.
- [NO_CODE]: The skill does not include any executable scripts, shell commands, or external package dependencies.
- [DATA_EXPOSURE]: The skill uses abstract configuration paths (e.g.,
layout.*,roots.*) and does not access sensitive system files or credentials. - [PROMPT_INJECTION]: The
ROLE.mdfile actually implements safety guidelines by defining a 'secretary' persona that requires explicit user grants and prevents unilateral changes to the environment.
Audit Metadata