agenticros@0.7.24
AgenticROS - agentic AI for ROS-powered robots. Single CLI to launch real-robot or simulated demos, manage configuration, and inspect status.
AI Security Review
scanned 23d ago · by lpm-firewall-aiThis is a guarded, first-party agent-extension setup capability that warrants a warning under the agent integration policy. The inspected source does not support a malicious or publish-block verdict.
Decision evidence
public snapshot- The package metadata contains a publication-only lifecycle script, not an install lifecycle hook.
- The CLI registers an AgenticROS MCP server in global or project Codex configuration.
- The configuration writer merges and writes the Codex MCP configuration file.
- The init flow asks before configuring MCP clients, then invokes the configuration operation.
- The OpenClaw helper can add plugin tool names to its allowed-tools configuration.
- No unconsented npm install-time mutation was found.
- The agent configuration operations are exposed through explicit CLI setup or a confirmation in the init flow.
Source & flagged code
23 flagged · loading sourcePackage source references child process execution.
dist/util/mcp-discovery.jsView on unpkg · L16Source file is highly similar to a previously finalized malicious package; route for source-aware review.
dist/util/mcp-discovery.jsView on unpkgFindings
Affected versions and remediation
This report applies to agenticros@0.7.24.
See all versions of agenticros for other recorded verdicts.
- Review the evidence and your use of agenticros@0.7.24 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.