dsh-versatileds-plugin@0.2.9
AI Security Review
scanned 10d ago · by lpm-firewall-aiThe endpoint is configurable independently from the saved provider key, and chat requests transmit that key to it. The default endpoint is aligned with the key, so the source supports a conditional exposure warning rather than a confirmed malicious attack.
Decision evidence
public snapshot- The model URL accepts any OpenAI-compatible endpoint, while the configured default is DeepSeek.
- The API key can come from configuration, an environment variable, or a local file.
- Chat requests send the key as a bearer token alongside chat history to the configured URL.
- Incoming chat messages can activate model reply generation.
- The Bilibili runtime hint passes video candidates to the DSH language model for selection.
- The default model endpoint is the intended DeepSeek service.
- The reviewed source does not establish a fixed, unrelated recipient or a hidden install-time transfer.
Source & flagged code
5 flaggedFindings
Affected versions and remediation
This report applies to dsh-versatileds-plugin@0.2.9.
See all versions of dsh-versatileds-plugin for other recorded verdicts.
- Review the evidence and your use of dsh-versatileds-plugin@0.2.9 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.