enhance-prompt
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references best practice guidelines from the official Stitch documentation at https://stitch.withgoogle.com/docs/learn/prompting/.
- [PROMPT_INJECTION]: The skill architecture includes an indirect prompt injection surface where it reads and incorporates content from a local
DESIGN.mdfile into its prompt generation logic. - Ingestion points: Local
DESIGN.mdfile (referenced inSKILL.mdStep 2). - Boundary markers: No explicit delimiters or instructions to disregard embedded instructions within the file content were identified.
- Capability inventory: The skill uses
ReadandWritetools to extract context and save the resulting enhanced prompts to the file system. - Sanitization: No input validation or sanitization of the
DESIGN.mdcontent is performed before interpolation into the agent's output.
Audit Metadata