custom-code-management
Fail
Audited by Snyk on Feb 15, 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 requires the agent to accept and pass user-provided script sourceCode verbatim to the MCP (via add_inline_site_script), so any embedded API keys or secrets in that script would be included directly in the agent's output/requests and thus risk exfiltration.
Audit Metadata