invoke-capability
Fail
Audited by Snyk on Apr 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 prompt explicitly mandates handing the user's text verbatim (via a --prompt CLI flag and forwarding outputs verbatim), so any API keys, tokens, or passwords present in user messages would be included and transmitted unchanged—creating a direct secret-exfiltration pathway.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata