@p4code/cli@0.6.9
P4 Code coding agent server and command-line client
AI Security Review
scanned 25d ago · by lpm-firewall-aiThe source implements explicit, potentially persistent writes to AI-agent control files, including automatic synchronization once configured. There is no evidence of install-time abuse, secret theft, or a concrete malicious payload.
Decision evidence
public snapshot- The package exposes the p4c executable and has no npm lifecycle hook in its manifest.
- The CLI offers explicit commands to share user memory files and subagent definitions.
- The sync implementation writes validated agent-definition markdown into an agent root.
- The bundled client describes overwriting files in user skill, provider configuration, and subagent-definition directories.
- No install-time lifecycle script was found.
- The sharing command states that items do not share until named with publish.
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@0.6.9.
See all versions of @p4code/cli for other recorded verdicts.
- Review the evidence and your use of @p4code/cli@0.6.9 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.