lisa-review-implementation

Fail

Audited by Snyk on Feb 16, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 0.90). The skill reads project and template files and emits verbatim diffs and file contents (and can copy files back), so any secrets present in those files (API keys, tokens, passwords) would be included in the agent's output or writes, enabling exfiltration.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 03:43 AM