turn2spec
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill functions as a documentation assistant, with operations limited to reading and writing files in the docs/ and plugins/ directories.
- [PROMPT_INJECTION]: The skill processes untrusted content from user-provided documents to generate its output. Ingestion points: Input is received via $ARGUMENTS and files read from docs/sketches/ or docs/plans/. Boundary markers: No explicit delimiters or ignore-instructions are defined for the source material. Capability inventory: Uses Read, Write, and Edit tools for document management; no access to shell or network tools. Sanitization: Instructions mandate the removal of technical implementation details, focusing solely on business logic and requirements. This surface is considered a normal part of the documentation transformation workflow.
Audit Metadata