@whalent/agent-core@0.3.462
Core runtime for Whalent Agent
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThe package has no install lifecycle trigger, so blocking is not supported. Its runtime configuration injection capability is a real AI-agent control-surface risk and is best treated as user-invoked capability abuse.
Decision evidence
public snapshot- The manifest exposes a CLI but contains no npm lifecycle hook.
- The MCP bundle contains a routine that constructs a config.toml path and updates MCP-server configuration.
- MCP execution is gated by direct runtime invocation, rather than package installation.
- No preinstall, install, postinstall, or self-dependency is declared.
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@0.3.462.
See all versions of @whalent/agent-core for other recorded verdicts.
- Review the evidence and your use of @whalent/agent-core@0.3.462 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.