enhance-prompt
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: References official documentation from Google's Stitch platform. This is a neutral reference to a well-known service for instructional guidelines.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as part of its design for file-based configuration.\n
- Ingestion points: Reads local
DESIGN.mdfiles within the project workspace as described inSKILL.md.\n - Boundary markers: Content from external files is interpolated without specific delimiters or instructions to disregard embedded commands.\n
- Capability inventory: The skill is configured with
ReadandWritetool permissions in theSKILL.mdfrontmatter.\n - Sanitization: Content retrieved from local files is not sanitized or validated before being included in the generated prompt.
Audit Metadata