migrate-to-shoehorn
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to search and read the contents of local test files (
*.test.ts,*.spec.ts). This ingestion of untrusted data creates a potential surface for indirect prompt injection if instructions are embedded within the code being processed. - Ingestion points: Content of files identified by
grepinSKILL.md. - Boundary markers: None present; the skill lacks specific delimiters or instructions to ignore potential commands within the files.
- Capability inventory: File read and write operations are required for the migration workflow.
- Sanitization: No validation or sanitization of file content is performed before the agent processes it for refactoring.
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the
@total-typescript/shoehornpackage from the public NPM registry. This is an expected dependency for the skill's stated purpose of migrating code to that specific library.
Audit Metadata