stitch-enhance-prompt
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill description mentions a source from Google Labs, which is a well-known and trusted organization. This reference is documented as safe.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided UI requests to generate structured outputs, which creates an attack surface for indirect prompt injection. However, because the skill does not use any tools or possess capabilities like network or file access, this surface is considered safe. * Ingestion points: User input parsed in Step 1 as defined in SKILL.md. * Boundary markers: None present. * Capability inventory: None; the skill has no authorized tools or dangerous command execution. * Sanitization: None present.
Audit Metadata