ask-gemini
Fail
Audited by Snyk on Aug 20, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.80). The skill embeds user-supplied ARGUMENTS into local CLI commands and explicitly requires saving the "final prompt" and "Gemini output (raw)" verbatim, which forces the agent to output any secrets present in those prompts/outputs.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata