migrate-to-shoehorn

Pass

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes project source code files (*.test.ts, *.spec.ts) as input for its migration workflow, which represents a potential attack surface if those files contain malicious instructions. * Ingestion points: Local test files identified through grep and processed for text replacement. * Boundary markers: Absent; there are no instructions to the agent to disregard natural language commands that might be found in code comments or string literals. * Capability inventory: The skill utilizes npm for package installation, grep for file discovery, and performs file modifications. * Sanitization: Absent; the skill does not specify any sanitization or validation for the content of the files it reads.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the @total-typescript/shoehorn package using npm. This is a reference to a well-known community package on a standard registry.
  • [COMMAND_EXECUTION]: The workflow involves executing local shell commands, specifically npm for dependency management and grep for identifying target files for the migration.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 12, 2026, 02:51 AM