lesson-learned

Fail

Audited by Snyk on Jun 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 explicitly instructs the agent to quote actual changed code and reference specific file lines from diffs, which can force the LLM to reproduce any secrets (API keys, tokens, passwords) present in those changes verbatim and thus risks exfiltration.

Issues (1)

W007
HIGH

Insecure credential handling detected in skill instructions.

Audit Metadata
Risk Level
HIGH
Analyzed
Jun 27, 2026, 12:15 PM
Issues
1