can
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 disclosed CAN debugging toolkit with no obfuscation, pretexts, or exfiltration, but it sends bus frames without confirmation after auto-selecting a sole interface and persisting that choice, which the user may not expect.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The monitor, log, and stats commands ingest raw CAN frames from the physical bus, which anyone with bus access can inject, but those payloads are binary hex bytes or DBC-decoded numeric signals rather than free text, and the agent must actively run these commands.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata