yy-check-skills-consistency

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes git commands such as git diff and git status to identify changes in the directory structure. It also modifies the scripts/install-skills.ts file, which is a functional script executed during the installation process, to maintain an array of skill names.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from the local file system to modify project files. \n
  • Ingestion points: Reads directory names from the skills/ folder and descriptions from the frontmatter of SKILL.md files.\n
  • Boundary markers: None; the skill directly interpolates external strings into the README and script files.\n
  • Capability inventory: File system read/write access and the ability to modify executable TypeScript files.\n
  • Sanitization: There is no mention of sanitization or escaping for the data written into the oldSkillNamesToDelete array in scripts/install-skills.ts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 02:56 AM
Security Audit — agent-trust-hub — yy-check-skills-consistency