migrate-to-shoehorn

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill workflow includes the installation of the @total-typescript/shoehorn package from the npm registry.
  • [COMMAND_EXECUTION]: The instructions require the agent to execute shell commands, specifically npm install for dependency management and grep for searching the local filesystem for specific code patterns.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and modify content from user-provided test files, creating a potential surface for indirect prompt injection if those files contain instructions targeting the agent.
  • Ingestion points: Local TypeScript test files (*.test.ts and *.spec.ts) identified and read during the migration process.
  • Boundary markers: Absent; there are no specific instructions or delimiters provided to ensure the agent ignores or sanitizes natural language instructions found within the code comments or strings of the files being processed.
  • Capability inventory: The agent is granted capabilities to execute shell commands and perform file modifications.
  • Sanitization: No sanitization or validation logic is defined for the content extracted from the target test files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 10:09 PM
Security Audit — agent-trust-hub — migrate-to-shoehorn