stitch-uviewpro-components

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). At runtime the skill calls Stitch MCP get_screen to obtain htmlCode.downloadUrl, then runs scripts/fetch-stitch.sh to download and parse the Stitch HTML (outsider-authored public design content) into LLM-readable prose/context for conversion.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill fetches Stitch screen HTML at runtime (via the screen's htmlCode.downloadUrl and the example Stitch URL https://stitch.withgoogle.com/projects/3492931393329678076?node-id=375b1aadc9cb45209bee8ad4f69af450) using scripts/fetch-stitch.sh (curl), and that downloaded HTML is parsed and used to drive the agent's prompt/content generation, so it is a runtime external dependency that directly controls the agent's output.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)