gpt-review

Fail

Audited by Snyk on Jul 27, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 0.80). The prompt requires returning the subagent's exact, verbatim output while also requesting "necessary context" for the review, which creates a real risk the model will echo any secrets present in that context (e.g., API keys, passwords) back to the user.

Issues (1)

W007
HIGH

Insecure credential handling detected in skill instructions.

Audit Metadata
Risk Level
HIGH
Analyzed
Jul 27, 2026, 03:51 AM
Issues
1
Security Audit — snyk — gpt-review