@p4code/cli@0.6.22
P4 Code coding agent server and command-line client
AI Security Review
scanned 24d ago · by lpm-firewall-aiThe package has concrete agent configuration and runtime-install capabilities, but no evidence of an automatic lifecycle attack, credential theft, or covert exfiltration. Treat this as a guarded agent-extension risk rather than malware.
Decision evidence
public snapshot- Package metadata exposes a command-line entry point and contains no lifecycle hook.
- The command bundle can rewrite Claude MCP server configuration files.
- The command bundle can replace managed agent skill directories.
- A server-runtime path installs a pinned release of this package with npm.
- No install-time lifecycle hook was found.
- The identified client assets are a file-icon mapping and an API schema, not configuration writes.
Source & flagged code
22 flagged · loading sourceSource archives sensitive local configuration and publishes encoded chunks through an authenticated package-registry request.
dist/bin.mjsView on unpkg · L13Source appears to send environment or credential material to an external endpoint.
dist/bin.mjsView on unpkg · L13Findings
Affected versions and remediation
This report applies to @p4code/cli@0.6.22.
See all versions of @p4code/cli for other recorded verdicts.
- Review the evidence and your use of @p4code/cli@0.6.22 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.