react:components
Converts Stitch designs into modular Vite and React components using system-level networking and AST-based validation.
Security
3 findings — 1 high severity, 2 medium severity. 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
Insecure credential handling detected (high risk: 1.00). The prompt instructs the agent to place design download URLs verbatim into shell commands (e.g., bash scripts using "[htmlCode.downloadUrl]" and "[screenshot.downloadUrl]"), and those URLs can include signed tokens or secret query params, so the LLM would need to handle and emit secret values directly.
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
Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and processes design HTML and screenshot URLs returned by the Stitch MCP (see SKILL.md retrieval/networking steps 2–4, scripts/fetch-stitch.sh, and resources/stitch-api-reference.md), which are untrusted/user-provided web content that the agent must parse (extract tailwind config, asset URLs, metadata) and use to drive code generation and tooling—allowing third-party content to influence actions.
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
Potentially malicious external URL detected (high risk: 0.90). The skill calls scripts/fetch-stitch.sh to curl the Stitch MCP signed URLs (e.g., the htmlCode.downloadUrl and screenshot.downloadUrl) at runtime, and the downloaded HTML is parsed (including a localized tailwind.config) and used to drive generation/mapping decisions—so remote content fetched from those URLs directly controls the agent's instructions/output.
- Repository
- google-labs-code/stitch-skills
- Commit
ad0b5cc
- 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.