analyze-prompt
Fail
Audited by Snyk on Mar 5, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). This skill reads a user-supplied prompt file completely and produces quoted/refactored output of that content, so if the file contains API keys, tokens, or passwords the agent may copy them verbatim into its output, causing credential exfiltration.
Audit Metadata