claw-helper
Fail
Audited by Snyk on Mar 9, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.90). High risk: the skill mandates using a CLI command form
openclaw config set <key> <value>, which encourages embedding configuration values (including secrets/API keys/passwords) directly as command arguments, forcing the LLM to handle and potentially emit secret values verbatim.
Audit Metadata