gemini
Fail
Audited by Snyk on Jun 13, 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 instructs assembling and sending full diffs and contextual change data (DIFF, CONTEXT) into the Gemini prompt, so any API keys, tokens, or passwords present in those files will be passed verbatim to the model and may be echoed in the review, creating an exfiltration risk.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata