aicodeman@1.26.1
Mission control for AI coding agents - run 20 autonomous agents with real-time monitoring and session persistence
AI Security Review
scanned 2mo ago · by lpm-firewall-aiThe source establishes unconsented install-time project mutation and autostart, but it does not establish the full lifecycle self-dependency chain, a foreign AI-agent control-surface write, or covert exfiltration. The credential use is confined to an authenticated, feature-gated relay to Anthropic.
Decision evidence
public snapshot- The package runs a postinstall script automatically.
- Postinstall overwrites the consumer checkout’s .git/hooks/pre-commit file.
- Postinstall starts a detached local web-server process unless opted out.
- Runtime code can read Claude OAuth credentials and send them as a bearer token to Anthropic’s voice endpoint.
- The credential relay is reachable only through a guarded voice WebSocket route and is feature-gated.
- The configured upstream is api.anthropic.com, consistent with the stated speech relay.
- No self-dependency, hidden remote payload, or foreign AI-agent configuration write was found.
Source & flagged code
29 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgPackage source references child process execution.
dist/ai-checker-base.jsView on unpkg · L24Findings
Affected versions and remediation
This report applies to aicodeman@1.26.1.
See all versions of aicodeman for other recorded verdicts.
- Review the evidence and your use of aicodeman@1.26.1 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.