migrate-to-shoehorn

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the @total-typescript/shoehorn package from the public npm registry. This is a legitimate, well-known utility library in the TypeScript ecosystem.
  • [COMMAND_EXECUTION]: The workflow involves executing grep to search for type assertions in local project files and suggests automated code replacements to migrate patterns. These are standard operations for a code migration tool.
  • [PROMPT_INJECTION]: Indirect Prompt Injection: The skill identifies an attack surface by processing project files and user-provided paths.
  • Ingestion points: The agent reads content from test files (e.g., *.test.ts) specified by the user in the 'Gather requirements' step.
  • Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded commands within the files being migrated.
  • Capability inventory: The skill performs package installation (npm install), file searching (grep), and code modification (replacing strings).
  • Sanitization: No explicit sanitization or validation of the file content is mentioned before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 03:36 AM
Security Audit — agent-trust-hub — migrate-to-shoehorn