skills/brianlovin/claude-config/knip/Gen Agent Trust Hub

knip

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The tool scans project files and can delete files or modify configuration, creating a surface for injection from the codebase. Evidence: 1. Ingestion: Project files; 2. Boundary markers: Absent; 3. Capability inventory: File deletion and package.json modification; 4. Sanitization: Absent.
  • Unverifiable Dependencies (LOW): The skill installs the 'knip' package from npm. This is a medium-risk action (unverifiable dependency) downgraded to low as it is the primary purpose of the skill.
  • Command Execution (LOW): The skill executes shell commands via npx to analyze and clean the codebase.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:53 PM