migrate-to-shoehorn
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill involves reading and modifying external data in the form of project source code files.
- Ingestion points: The skill searches for and reads content from
.test.tsand.spec.tsfiles via shell commands. - Boundary markers: There are no explicit instructions to use delimiters or ignore potentially malicious instructions embedded in the code comments of the files being processed.
- Capability inventory: The skill performs file system reads and modifications, along with local command execution for searching.
- Sanitization: No specific validation or sanitization of the file content is performed before the agent processes and acts upon it.
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the
@total-typescript/shoehornpackage from the public npm registry to the local environment. - [COMMAND_EXECUTION]: The workflow utilizes the
greputility to recursively search the file system for specific TypeScript patterns, which is a standard part of the migration automation process.
Audit Metadata