@decoopus/claude-setup@1.0.8
AI Security Review
scanned 9d ago · by lpm-firewall-aiThe inspected source implements an explicitly described, user-invoked third-party gateway setup and stores the API key supplied for that configuration. No install-time trigger or separate credential exfiltration behavior was found.
Decision evidence
public snapshot- package.json exposes bin/cli.js as the setup command and lists only a start script, with no install lifecycle hook.
- The CLI describes its purpose as configuring Claude Desktop with a third-party inference gateway and defaults that gateway to https://api-anthropic.help.
- When run, the CLI prompts for an API key and stores the supplied key and gateway URL in Claude Desktop configuration.
- The gateway URL can be overridden with a command-line option; the reviewed CLI source contains no code that sends the key over the network.
Source & flagged code
6 flagged · loading sourcepackage.json exposes bin/cli.js as the setup command and lists only a start script, with no install lifecycle hook.
package.jsonView on unpkg · L4package.json exposes bin/cli.js as the setup command and lists only a start script, with no install lifecycle hook.
package.jsonView on unpkg · L15The CLI describes its purpose as configuring Claude Desktop with a third-party inference gateway and defaults that gateway to https://api-anthropic.help.
Findings
Affected versions and remediation
This report applies to @decoopus/claude-setup@1.0.8.
See all versions of @decoopus/claude-setup for other recorded verdicts.
- Review the evidence and your use of @decoopus/claude-setup@1.0.8 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.