prompt-engine
Fail
Audited by Snyk on Feb 15, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.90). The engine substitutes user-provided placeholders directly into prompts (after light sanitization that doesn't remove typical API-key characters), so a secret supplied as a placeholder would be embedded verbatim and could be exfiltrated.
Audit Metadata