design-pro
Fail
Audited by Snyk on Nov 20, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill is a disclosed design workflow, but it globally installs a third-party pack non-interactively (
-y) and can attach to the user's signed-in Chrome session, both beyond what the design task strictly needs; this is risky without malicious intent.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow fetches outsider-authored web pages only when the user names sites for inspiration or gives a URL to audit, so the agent must be pointed at them and nothing is pushed into a feed it monitors.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The setup command
npx skills add Melvynx/ai-design-profetches and installs skill material from an individually owned GitHub repository, which is an unofficial but attributable source with no concrete warning signs, so the tier is medium.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill's global
npx skills add ... -g -a claude-code -a codexinstallation changes persistent agent integrations, but no explicit irreversible operational loss is established, so it fails gate 2 and stays at low.
Issues (4)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata