@p4code/cli@0.8.1
P4 Code coding agent server and command-line client
AI Security Review
scanned 8d ago · by lpm-firewall-aiThe manifest has no install hook, and the flagged worker code resolves to a CLI history feature and Claude directory handling. The evaluation and socket indicators are bounded checks, and the inspected client code handles sanitized rendering and file previews; no concrete malicious behavior was found.
Decision evidence
public snapshot- package.json declares the p4c entrypoint and contains no lifecycle hook.
- The reported agent-related code resolves the configured Claude directory and project name.
- The history worker handles session reading or forking, loads local session data, and returns JSON to its caller; the CLI dispatches it through a hidden subcommand.
- The apparent evaluation check only tests whether an empty function can be constructed; the socket helper makes a short connection probe and destroys the socket.
- The client assets sanitize rendered content and use range requests to load file previews.
- The bundle includes process and network APIs, and the worker can read Claude session history; these capabilities match the CLI’s functions and do not establish malicious behavior.
- Static indicators include a function-construction check and socket connection code, but the inspected code does not show downloaded-code execution or a reverse shell.
Source & flagged code
14 flagged · loading sourceSource appears to send environment or credential material to an external endpoint.
dist/claudeHistoryWorker-v_0uyLGp.mjsView on unpkg · L11Source matches reverse-shell style process and socket wiring.
dist/claudeHistoryWorker-v_0uyLGp.mjsView on unpkg · L11Findings
Affected versions and remediation
This report applies to @p4code/cli@0.8.1.
See all versions of @p4code/cli for other recorded verdicts.
- Review the evidence and your use of @p4code/cli@0.8.1 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.