stitch-sdk-usage
Use the Stitch SDK to generate, edit, and iterate on UI screens from text prompts, manage projects, and retrieve screen HTML/images. Use when the user wants to consume the SDK in their application.
64
76%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Fix and improve this skill with Tessl
tessl review fix ./.agents/skills/stitch-sdk-usage/SKILL.mdSecurity
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill includes a code example that hardcodes an API key (apiKey: "your-api-key") — instructing embedding secrets verbatim in generated code/outputs — which creates an exfiltration risk.
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The required runtime workflow allows an agent to pass a user-controlled free-text `prompt` (e.g., via `stitch.callTool("generate_screen_from_text", { ... prompt })`), which is directly ingested by the Stitch generation API.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The SDK example configures and uses the MCP base URL "https://stitch.googleapis.com/mcp" at runtime (StitchToolClient.callTool / listTools), which invokes remote MCP tools that execute server-side tooling and can directly control agent behavior.
- Repository
- google-labs-code/stitch-sdk
- Commit
575a9fb
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.