used
Fail
Audited by Snyk on Jun 14, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.90). The skill instructs the model to scan the conversation and extract tag/tool/plugin values verbatim (e.g., contents, mcp__... tool names), so any secrets present in those fields would be copied into the output and could be exfiltrated.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata