migrate-to-shoehorn

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the @total-typescript/shoehorn package via npm. This is an expected operation for the skill's primary purpose and targets a well-known utility library in the TypeScript ecosystem.
  • [COMMAND_EXECUTION]: Uses a standard grep command to identify migration targets within the user's project files. The command is scoped to specific file extensions (*.test.ts, *.spec.ts) and targets a static string pattern.
  • [PROMPT_INJECTION]: As the skill processes and refactors external source code files, it possesses an inherent surface for indirect prompt injection.
  • Ingestion points: Reads content from files matching *.test.ts and *.spec.ts found via grep.
  • Boundary markers: None defined in the skill instructions.
  • Capability inventory: The skill performs file system modifications and package installations.
  • Sanitization: No specific sanitization of the ingested code is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 10:24 AM
Security Audit — agent-trust-hub — migrate-to-shoehorn