stitch-vue-bootstrap-components
Warn
Audited by Snyk on Apr 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's required workflow calls Stitch MCP get_screen to obtain htmlCode.downloadUrl and instructs using scripts/fetch-stitch.sh to download and parse that Stitch-hosted HTML (user-generated/untrusted design content), which the agent must read and interpret to drive component conversion.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill's scripts/fetch-stitch.sh explicitly curl's a runtime-provided htmlCode.downloadUrl (invoked as bash scripts/fetch-stitch.sh "<htmlCode.downloadUrl>" … and implemented as curl -L -f -sS "$URL"), which downloads external Stitch HTML that is then parsed and injected into the agent's conversion flow and thus directly controls the agent's prompts/outputs.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata