inbox
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: 1.00). The skill requires the model to display pre-injected inbox messages verbatim, so any API keys, tokens, or passwords present in those messages would be output by the LLM and could be exfiltrated.
Audit Metadata