craft-explore
Fail
Audited by Snyk on Nov 15, 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 design-exploration workflow with no malicious intent toward the user, but the HTML adapter tells the agent to shape its headless-browser command (one plain command, no
cdor&&, output inside the working folder) so it fits typical permission rules, which weakens the user's approval checks beyond what the task needs.
Issues (1)
E004
CRITICALPrompt injection detected in skill instructions.
Audit Metadata