pr

Fail

Audited by Snyk on Mar 13, 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 asks the agent to "review the full conversation" and automatically write conversation context into the PR description, which could cause the LLM to copy any API keys/secrets present in the chat verbatim into PR text (exfiltration risk), even though it doesn't explicitly ask for secrets otherwise.

Issues (1)

W007
HIGH

Insecure credential handling detected in skill instructions.

Audit Metadata
Risk Level
HIGH
Analyzed
Mar 13, 2026, 10:12 PM
Issues
1