@whalent/agent@0.3.504
Stable wrapper for Whalent Agent core runtime
AI Security Review
scanned 10d ago · by lpm-firewall-aiSource inspection found a first-party agent extension capability in the obfuscated MCP bundle, but did not establish its activation caller or an unconsented attack. Warn because the capability can place fetched skill content where an agent may load it.
Decision evidence
public snapshot- package.json exposes dist/index.cjs as the CLI entrypoint.
- dist/mcp.cjs contains a skill installer that writes files into platform, workspace, or managed skill directories.
- dist/mcp.cjs fetches skill files from a configured API using a bearer token, then passes them to the installer.
- The bundle is heavily obfuscated, and the caller that activates the skill installer was not resolved.
- package.json lists prepublishOnly as a build command; it shows no preinstall, install, or postinstall hook.
- dist/mcp.cjs checks skill file paths to keep writes within the selected skill directory.
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@0.3.504.
See all versions of @whalent/agent for other recorded verdicts.
- Review the evidence and your use of @whalent/agent@0.3.504 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.