domain-language
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill functions as a documentation assistant that extracts and standardizes project terminology. Its operations are restricted to reading local project files and generating Markdown documentation.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface as it reads content from
.scratchpad/<slug>/interview-decisions.mdand project source code. Although this ingestion lacks explicit boundary markers or sanitization, the risk is negligible as the skill only generates static Markdown documentation and does not execute code or perform network operations. Mandatory Evidence Chain: 1. Ingestion points:.scratchpad/<slug>/interview-decisions.mdand project source code. 2. Boundary markers: None. 3. Capability inventory: Local file-write (Markdown). 4. Sanitization: None.
Audit Metadata