graph-audit

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a project-specific tool for auditing Skill Graph metadata. It defines a set of Node.js-based verification scripts (e.g., skill-lint.js, skill-graph-drift.js) and JSON schemas to maintain consistency between SKILL.md source files and audit-state.json sidecars.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute auditing scripts. These commands (e.g., node scripts/skill-lint.js, node scripts/generate-manifest.js) are standard development operations for the intended project environment and operate on local repository artifacts.
  • [EXTERNAL_DOWNLOADS]: The skill references standard project resources and official schemas. The skill_graph_source_repo points to the author's official GitHub repository (https://github.com/jacob-balslev/skill-graph), which is consistent with the skill's purpose and author context.
  • [PROMPT_INJECTION]: No patterns of prompt injection, safety bypass, or role-play instructions were detected. The instructions focus strictly on the technical domain of graph auditing and metadata integrity.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 04:35 AM
Security Audit — agent-trust-hub — graph-audit