@p4code/cli@0.8.10
P4 Code coding agent server and command-line client
AI Security Review
scanned 6d ago · by lpm-firewall-aiSource inspection found no lifecycle hooks or concrete attack behavior. The scanner’s shell and credential findings are not supported by the inspected worker entry, which performs Claude history operations; local shell execution is consistent with the package’s coding-agent function.
Decision evidence
public snapshot- package.json defines a CLI entry and no lifecycle scripts.
- The flagged worker accepts only Claude history operations: reading session messages or forking a session.
- The shell code starts a local Bash process with piped input and output; this is consistent with a coding agent’s command execution capability.
- The flagged configuration location reads Claude configuration and project directory values and compares paths; the inspected code does not show an agent configuration write.
- The other flagged files inspected are dependency or frontend asset bundles.
- The package exposes command execution capability, but the inspected worker entry does not dispatch shell commands.
- No credential transfer, reverse network shell, or agent configuration mutation was established in the inspected source.
Source & flagged code
14 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@0.8.10.
See all versions of @p4code/cli for other recorded verdicts.
- Review the evidence and your use of @p4code/cli@0.8.10 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.