ochrana-dat-zaku

Fail

Audited by Snyk on Nov 14, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill's only outbound action is an agent-initiated GitHub issue to the author's repository about changed legal sources, which is consent-gated and disclosed but still sends an external report to the vendor on the user's behalf, so I classify it as a risky but non-malicious medium under the recall-first override.

Issues (1)

E004
CRITICAL

Prompt injection detected in skill instructions.

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 14, 2026, 06:50 PM
Issues
1