learn
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands for file management tasks, including directory creation (
mkdir) and collision detection. These operations are restricted to relevant agent-specific folders and are used for benign utility functions. - [PROMPT_INJECTION]: The skill handles untrusted data which provides a surface for indirect prompt injection (Category 8). Ingestion points: Content is sourced from user inputs and local knowledge files. Boundary markers: The workflow uses Markdown sections and frontmatter for structure. Capability inventory: Actions are restricted to file system operations in
.agentsdirectories and shell-based utility checks. Sanitization: Slugs are sanitized to prevent command or path injection via filenames.
Audit Metadata