oh-langfuse@1.2.1
Use npm scripts to configure Claude Code / OpenCode / Codex / DeepSeek Harness with Langfuse tracing.
AI Security Review
scanned 9d ago · by lpm-firewall-aiThe manifest has no npm install lifecycle hook, and the flagged agent configuration writes are reached through explicit setup commands. Automatic updates are gated by an explicit auto setting or user confirmation, so the inspected behavior supports normal Langfuse setup rather than a confirmed attack.
Decision evidence
public snapshot- The manifest exposes setup and update commands but defines no npm preinstall, install, or postinstall hook.
- Setup runs from an explicit CLI command. Codex setup writes its hook and Langfuse configuration under the Codex home directory.
- Claude setup writes the Langfuse hook under the Claude hooks directory and adds Langfuse settings to Claude configuration when setup runs.
- The updater checks the npm registry and invokes setup scripts for detected targets; automatic updates require an explicit auto setting, while the default is to ask.
- The flagged CLI runtime location contains argument parsing, and its setup dispatch is reached only for the setup command.
Source & flagged code
8 flagged · loading sourceSource gates dangerous network, credential, or execution behavior behind CI, host, platform, time, or geo fingerprint checks.
Findings
Affected versions and remediation
This report applies to oh-langfuse@1.2.1.
See all versions of oh-langfuse for other recorded verdicts.
- Review the evidence and your use of oh-langfuse@1.2.1 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.