@p4code/cli@0.8.14
P4 Code coding agent server and command-line client
AI Security Review
scanned 6d ago · by lpm-firewall-aiThe manifest exposes a CLI without an install hook, and the high-risk matches inspected resolve to local shell support, a runtime capability check, and an internal Claude history feature. The source inspection did not establish a concrete attack surface.
Decision evidence
public snapshot- The manifest identifies a CLI entrypoint and shows no install lifecycle hook or runtime dependency on itself.
- The entrypoint dispatches commands only when the package is invoked as the CLI.
- The indicated Claude configuration location reads environment values to select a configuration directory and project name.
- The history worker accepts a session ID and handles only message retrieval or session forking; an internal CLI command hosts it.
- The flagged process code starts a local shell for command execution, and the dynamic function match is a guarded capability check.
- Other required review locations contain Effect and schema runtime code, frontend asset loaders, and an ACP JSON-RPC stream parser.
- The inspected source does not support the scanner's reverse-shell or hidden-payload labels.
Source & flagged code
13 flagged · loading sourcePackage source references child process execution.
dist/AcpMcpStdioBridge-BL9bAh79.mjsView on unpkg · L4Source appears to send environment or credential material to an external endpoint.
dist/claudeHistoryWorker-BvaF6m2o.mjsFindings
Affected versions and remediation
This report applies to @p4code/cli@0.8.14.
See all versions of @p4code/cli for other recorded verdicts.
- Review the evidence and your use of @p4code/cli@0.8.14 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.