ask-claude
Fail
Audited by Snyk on Mar 4, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.90). The skill inserts user-provided ARGUMENTS verbatim into CLI commands and requires saving the "final prompt sent" and raw output to an artifact, so any secrets included in ARGUMENTS would be output/stored directly, creating an exfiltration risk.
Audit Metadata