stitch::manage-design-system
Manage design systems in Stitch using MCP tools. Includes retrieval of assets, creating/updating design systems in Stitch, and applying them to screens.
Security
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's upload example explicitly shows passing an API key on the command line (--api-key <API_KEY>), which requires embedding secrets verbatim into generated commands/output and is therefore high-risk.
Low
Low-risk findings.
1 low severity finding. 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 workflow can fetch outsider-authored HTML from existing Stitch screens via `get_screen` → `screenshot.downloadUrl`/`htmlCode.downloadUrl`, then ingests it as readable text using `read_url_content`, creating an indirect prompt-injection path from that fetched free text into the agent context.
- Repository
- google-labs-code/stitch-skills
- Commit
535b088
- 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.