@whalent/agent-core@0.3.486
Core runtime for Whalent Agent
AI Security Review
scanned 21d ago · by lpm-firewall-aiSource confirms caller-invoked agent configuration mutation, which the supplied policy classifies as warning-only. Obfuscation limits broader assurance but does not independently prove malicious intent.
Decision evidence
public snapshot- The manifest has no install lifecycle hooks or runtime self-dependency.
- The MCP request handler dispatches caller-selected tools.
- The MCP registration tool accepts server commands, arguments, and environment settings and passes them to agent configuration helpers.
- The Codex helper updates config.toml with the registered MCP server.
- No covert exfiltration or malicious install-time mutation was established.
- Inspected dynamic code generation belongs to bundled schema validation; string decoding alone does not establish a hidden executable 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-core@0.3.486.
See all versions of @whalent/agent-core for other recorded verdicts.
- Review the evidence and your use of @whalent/agent-core@0.3.486 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.