privilege-escalation
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: 1.00). The skill explicitly instructs searching for hardcoded credentials (e.g., seed scripts with
password:) and requires findings with file/line/snippet output, which can force the LLM to reproduce secret values verbatim in its reports.
Audit Metadata