stitch-loop
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is a manifest entry that provides triggers and high-level descriptions but does not include any executable scripts, binaries, or command-line instructions.
- [EXTERNAL_DOWNLOADS]: The documentation references an external repository at https://github.com/google-labs-code/skills for the full workflow. This is provided as an informational link for manual user installation from a well-known service.
- [INDIRECT_PROMPT_INJECTION]: The skill describes a feedback loop for design-to-code tasks which involves ingesting design briefs and UI critiques. 1. Ingestion points: Design-to-code feedback loop described in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: None (the skill ships with no executable scripts). 4. Sanitization: Absent, as there is no code present to perform sanitization.
Audit Metadata