@whalent/agent@0.3.456
Stable wrapper for Whalent Agent core runtime
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThe package has no install lifecycle hook, and the required MCP entry point gates daemon startup on direct invocation. Static inspection found no concrete malicious behavior.
Decision evidence
public snapshot- Package metadata declares a CLI entry point and contains no npm install lifecycle hook.
- The MCP daemon starts only when its file is directly run and requires a token before starting.
Source & flagged code
7 flagged · loading sourceSource contains an obfuscated payload loader that reconstructs and executes hidden code.
dist/mcp.cjsView on unpkg · L1A bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.
dist/mcp.cjsView on unpkgFindings
Affected versions and remediation
This report applies to @whalent/agent@0.3.456.
See all versions of @whalent/agent for other recorded verdicts.
- Review the evidence and your use of @whalent/agent@0.3.456 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.