@p4code/cli@0.6.18
P4 Code coding agent server and command-line client
AI Security Review
scanned 24d ago · by lpm-firewall-aiThis is a concrete, guarded AI-agent configuration capability and warrants a warning under the agent integration policy. Static inspection found no install hook or confirmed covert attack behavior.
Decision evidence
public snapshot- The package exposes a write-capable memory tool that can target AGENTS.md.
- The handler requires a thread capability and only accepts allowlisted memory filenames.
- The handler resolves the agent configuration directory and atomically appends caller-supplied text.
- The package metadata exposes a CLI entrypoint and contains no npm lifecycle hook.
- The configuration mutation is limited to named memory files and is capability-gated.
- No install-time hook or confirmed covert credential export was found.
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@0.6.18.
See all versions of @p4code/cli for other recorded verdicts.
- Review the evidence and your use of @p4code/cli@0.6.18 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.