oh-langfuse@1.1.1
Use npm scripts to configure Claude Code / OpenCode / Codex / DeepSeek Harness with Langfuse tracing.
AI Security Review
scanned 2mo ago · by lpm-firewall-aiThis is not an install-time malware chain because the manifest has no lifecycle hook and activation requires an explicit setup command. The package nevertheless persists broad agent telemetry and an automatic updater, so it warrants a warning.
Decision evidence
public snapshot- Explicit setup installs a Codex notify hook and replaces the Codex notify configuration.
- The hook reads Codex session records and flushes parsed turns to the configured Langfuse host.
- Setup creates a persistent helper that can run the latest release through npx when the packaged runtime is absent.
- OpenCode setup installs and patches a plugin, then writes shell-level Langfuse credentials and a command shim.
- package.json has no preinstall, install, or postinstall lifecycle hook.
- The mutations are reached through named setup commands rather than package installation.
- The observed collection and export behavior is consistent with the package's tracing function.
Source & flagged code
9 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@1.1.1.
See all versions of oh-langfuse for other recorded verdicts.
- Review the evidence and your use of oh-langfuse@1.1.1 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.