skill-register-care
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute specific Python scripts located in the user's local directories (~/.claude/skills/ and <USER_HOME>/OneDrive/.SYNC/scripts/) to inventory and synchronize skill metadata.
- [DYNAMIC_EXECUTION]: The skill contains a Python one-liner snippet in SKILL.md for parsing local JSON inventory data from the user's home directory.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface by ingesting data from local skill registry files and inventory logs. * Ingestion points: Local files ~/.skill-inventory.json, catalog-*.md, CLAUDE-CODE-SKILLS.md, and SKILL-MAP.md. * Boundary markers: Not present. * Capability inventory: Execution of Python scripts and shell commands as documented in SKILL.md. * Sanitization: No content sanitization is implemented for ingested metadata.
Audit Metadata