skill-expert

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a development tool designed to assist in the creation and validation of other agent skills. It contains no hidden instructions or malicious payloads.
  • [COMMAND_EXECUTION]: The skill uses local validation scripts (e.g., scripts/validate_skill_md.py) executed via the uv toolchain. These scripts perform static analysis on file content and do not initiate network connections or execute arbitrary commands.
  • [PROMPT_INJECTION]: The skill processes third-party skill files, which is a potential surface for indirect prompt injection. However, the risk is minimized by the skill's focus on structural validation and the use of safe parsing libraries. Ingestion points: Files within the user-specified directory processed by the validation scripts. Boundary markers: None identified for the target skill's natural language body. Capability inventory: Capability to create/edit files and execute local Python validation scripts. Sanitization: The skill employs yaml.safe_load() for frontmatter and uses regex for validating metadata constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 06:27 PM