@whalent/agent@0.3.471
Stable wrapper for Whalent Agent core runtime
AI Security Review
scanned 25d ago · by lpm-firewall-aiThis is a guarded agent-extension installation capability with remote content delivery, not evidence of automatic malware. The absence of an install lifecycle hook prevents a publish block, but the capability warrants a warning.
Decision evidence
public snapshot- The package metadata exposes a command-line entry point and contains no install lifecycle hook in its scripts.
- The MCP bundle accepts downloaded skill content and writes it into agent skill directories.
- The skill download request sends a bearer credential to the configured service URL.
- The skill-file writer rejects absolute paths and paths escaping its selected skill directory.
- No automatic install-time execution was found in the package metadata.
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@0.3.471.
See all versions of @whalent/agent for other recorded verdicts.
- Review the evidence and your use of @whalent/agent@0.3.471 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.