@whalent/agent-core@0.3.463
Core runtime for Whalent Agent
AI Security Review
scanned 25d ago · by lpm-firewall-aiThe source supports a warning for an agent-extension installation capability, but not a block: there is no automatic lifecycle execution or confirmed exfiltration, payload execution, or destructive action.
Decision evidence
public snapshot- The manifest exposes a command entry point and contains no lifecycle scripts.
- The MCP bundle identifies Claude and other agent platforms and derives platform-specific skill locations.
- The MCP bundle contains a skill installer that creates the resolved directory and writes supplied skill files.
- No install, preinstall, or postinstall hook was found in the manifest.
- No confirmed credential export, remote payload execution, or destructive behavior was established from the inspected paths.
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@0.3.463.
See all versions of @whalent/agent-core for other recorded verdicts.
- Review the evidence and your use of @whalent/agent-core@0.3.463 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.