Caveat verdict
ZeeLin Deep Research 深度研究
desearch
88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.
ZeeLin deep research platform skill using the user's own DESEARCH_API_KEY to call the documented desearch.zeelin.cn API; all network_out goes to the stated provider and credential_access reads the user's own key.
⚠ 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.
65
security
60
transparency
70
maintenance
Findings (1)
Pattern match critical
Possible hardcoded credential
SKILL.md · code · API_KEY="${DESEARCH_API_KEY}
Permissions & capabilities
Requires 1 system binary. (1 elevated: curl).
network_outcredential_access Is this flag fair?
Thanks — recorded.