skill-registry

Pass

Audited by Gen Agent Trust Hub on Jul 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs authorized file system operations within the project workspace, including creating the .atl/ directory, writing the skill-registry.md file, and updating the project's .gitignore file.
  • [PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection because it processes content from external files to generate summaries for a registry.
  • Ingestion points: The skill reads SKILL.md files from multiple global locations (e.g., ~/.claude/skills/, ~/.cursor/skills/) and project-specific convention files like CLAUDE.md and .cursorrules.
  • Boundary markers: The instructions do not define specific boundary markers or instructions to ignore potential commands embedded within the ingested files.
  • Capability inventory: The skill has permissions to write to the project directory, specifically the .atl/ folder and .gitignore file.
  • Sanitization: No sanitization or validation of the external markdown content is mentioned before it is processed into the final registry output.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 12, 2026, 05:26 PM
Security Audit — agent-trust-hub — skill-registry