skill-composition

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates with a restricted read-only scope, targeting only specific markdown files within the project's skill catalog, proposals, and fixtures directories.
  • [SAFE]: It employs strict extraction rules, looking only for specific hyphenated naming patterns while explicitly ignoring unrelated text or manner-only constraints.
  • [SAFE]: The instructions contain multiple explicit prohibitions against modifying files, executing remote code, or building repository-wide graphs, ensuring the agent remains within a limited analysis context.
  • [SAFE]: No network operations, credential usage, or persistence mechanisms were detected in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 04:48 PM
Security Audit — agent-trust-hub — skill-composition