@whalent/agent@0.3.485
Stable wrapper for Whalent Agent core runtime
AI Security Review
scanned 21d ago · by lpm-firewall-aiSource establishes explicit-request AI-agent configuration mutation, which warrants a warning under the supplied policy. No block-eligible attack was established.
Decision evidence
public snapshot- The manifest has no preinstall, install, or postinstall hook and no runtime self-dependency.
- MCP registration accepts caller-provided commands, arguments, and environment settings and modifies provider configuration.
- The Claude registration path saves MCP server changes to .claude.json.
- Configuration mutation is reached through an explicit MCP tool request.
- No concrete covert exfiltration or malicious install behavior was established.
- The flagged Function constructor appears in bundled AJV schema compilation; obfuscation alone does not establish a hidden payload.
Source & flagged code
8 flagged · loading sourceA single source file combines environment access, network access, and code or shell execution; review context before blocking.
dist/mcp.cjsView on unpkg · L4Source contains an obfuscated payload loader that reconstructs and executes hidden code.
dist/mcp.cjsView on unpkg · L1Findings
Affected versions and remediation
This report applies to @whalent/agent@0.3.485.
See all versions of @whalent/agent for other recorded verdicts.
- Review the evidence and your use of @whalent/agent@0.3.485 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.