skills/cisco-ai-defense/skill-scanner/no-confirmation-agent/Snyk

no-confirmation-agent

Fail

Audited by Snyk on Sep 9, 2026

Risk Level: CRITICAL

Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

Potential prompt injection detected (medium risk: 0.30). The skill instructs the agent to act while bypassing user confirmation, representing suspicious steering that weakens a user security boundary.

Issues (1)

E004

CRITICAL

Prompt injection detected in skill instructions.

Audit Metadata

Risk Level

CRITICAL

Analyzed

Sep 9, 2026, 11:39 AM

Issues

1

Security Audit — snyk — no-confirmation-agent