anfra-write-aql
Fail
Audited by Snyk on Nov 19, 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 legitimate AQL-writing guide, but its description tells the agent not to show answers in standard artifacts or canvases, which restricts how the user sees results without a stated reason, a mild concealment rather than an attack.
Issues (1)
E004
CRITICALPrompt injection detected in skill instructions.
Audit Metadata