skill-reviewer

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's logic is restricted to reading local markdown files and generating a checklist report based on predefined rules. It does not perform any sensitive operations, network requests, or code execution.
  • [PROMPT_INJECTION]: The skill handles third-party data from processed SKILL.md files. This creates a surface for indirect prompt injection; however, the skill's restricted capabilities (only generating a text report) and built-in validation rules (e.g., prohibiting XML tags in metadata) effectively mitigate the risk of the agent being misdirected.
  • [DATA_EXPOSURE]: While the skill reads files based on user-provided paths, it is explicitly constrained to 'SKILL.md' files within the repository scope, preventing arbitrary file access to sensitive system or configuration data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 04:24 PM