exa-ci-integration

Fail

Audited by Snyk on Feb 18, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The prompt includes an explicit example of setting an API key on the command line using gh secret set --body "sk_test_***", which requires or encourages embedding a secret value verbatim in commands/output and thus poses an exfiltration risk.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
HIGH
Analyzed
Feb 18, 2026, 09:17 PM