Caveat verdict
deepseek-toolkit
88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.
Advisory and documentation skill for DeepSeek API integration guidance, cost optimization, and model selection; contains no code execution, no data exfiltration, and no capability flags indicating elevated risk.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
70
security
70
transparency
70
maintenance
Findings (1)
Pattern match critical
Possible hardcoded credential
cost-optimization.md · code · api_key="sk-your-key
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.