review-comments

Fail

Audited by Snyk on Feb 28, 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 explicitly instructs the agent to read files and return comment text verbatim (e.g., Line {n}: "{comment}") and to apply edits, so any secrets present in comments or source (API keys, tokens, passwords) could be output by the LLM and thus exfiltrated.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 28, 2026, 01:14 AM