adversarial-review

Fail

Audited by Snyk on Apr 2, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The reviewer prompts require quoting "Evidence" from the submitted artifact (line/section/quote), so if the user pastes code, diffs, or configs containing API keys, tokens, or passwords the LLM is instructed to reproduce them verbatim, creating a high exfiltration risk.

Issues (1)

W007
HIGH

Insecure credential handling detected in skill instructions.

Audit Metadata
Risk Level
HIGH
Analyzed
Apr 2, 2026, 01:21 PM
Issues
1