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
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata