human-intervention

Fail

Audited by Snyk on Jun 18, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 0.80). This prompt mandates preserving the human's "EXACT words — preserve verbatim" in the Feedback section (and writing them into content.md files), which forces the agent to record and output any secrets the user might include (API keys, passwords, tokens), creating an exfiltration risk.

Issues (1)

W007
HIGH

Insecure credential handling detected in skill instructions.

Audit Metadata
Risk Level
HIGH
Analyzed
Jun 18, 2026, 11:34 PM
Issues
1
Security Audit — snyk — human-intervention