claude-skills-overview-2026
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFENO_CODEDYNAMIC_CONTEXT_INJECTION
Full Analysis
- [SAFE]: The skill is composed entirely of markdown-based documentation and usage examples. It does not implement any executable logic, scripts, or binary payloads. The instructions are purely educational, aimed at teaching the platform's runtime behavior.\n- [DYNAMIC_CONTEXT_INJECTION]: The skill provides reference material for the
!commandsyntax, a platform feature that allows shell output to be integrated into prompts. The examples provided (e.g., usingghfor pull request data) are standard, benign developer workflows for the Claude Code environment.
Audit Metadata