@whalent/agent-core@0.3.477
Core runtime for Whalent Agent
AI Security Review
scanned 23d ago · by lpm-firewall-aiDowngrade to a warning because the package can configure an MCP execution surface, but inspected evidence does not establish unconsented installation-time mutation, exfiltration, or a payload attack.
Decision evidence
public snapshot- The manifest exposes a command entrypoint and contains no npm lifecycle hook.
- The MCP bundle can add a supplied command, arguments, environment, or URL to a Claude MCP-server configuration.
- No install-time hook or confirmed credential export was found in the inspected manifest and configuration code.
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-core@0.3.477.
See all versions of @whalent/agent-core for other recorded verdicts.
- Review the evidence and your use of @whalent/agent-core@0.3.477 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.