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 requires embedding the design download URL (htmlCode.downloadUrl) verbatim into a bash command (and similarly uses fetched JSON fields in network calls), which can contain presigned tokens or sensitive query parameters, forcing the model to handle/output 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 retrieves and parses untrusted, user-provided design HTML and images via the signed htmlCode.downloadUrl and screenshot.downloadUrl (see SKILL.md "Metadata fetch" and "High-reliability download" steps and resources/stitch-api-reference.md) using scripts/fetch-stitch.sh, and the agent is required to read and act on that content (extract styles, asset URLs, and head config) as part of component generation—allowing page-origin content to influence generation and tool use.
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 invokes scripts/fetch-stitch.sh at runtime which runs curl on htmlCode.downloadUrl (a signed Google Cloud Storage download URL, e.g. https://storage.googleapis.com/...) and the fetched HTML/screenshot are used by the agent to drive component generation, meaning external content fetched at runtime directly controls the agent's outputs.
- Repository
- freekmurze/dotfiles
- Commit
355d067
- 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.