qqbot-media
Fail
Audited by Snyk on Mar 6, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E006: Malicious code pattern detected in skill scripts.
- Malicious code pattern detected (high risk: 0.90). The skill explicitly instructs the agent to always send local files via special tags (never refuse), requires absolute workspace paths, and automates reading/sending of local attachments—this creates a clear, intentional data-exfiltration vector though no remote-exec/backdoor code is present.
Audit Metadata