@programinglive/dev-workflow-mcp-server@1.17.1
MCP server to enforce development workflow discipline
AI Security Review
scanned 4d ago · by lpm-firewall-aiNo automatic attack behavior was identified. The explicit setup command changes broader AI-agent settings by registering a third-party plugin and writing project instructions, so this warrants a warning for agent capability abuse.
Decision evidence
public snapshot- The setup command adds a third-party OpenCode plugin and registers this package as a local MCP server in OpenCode configuration.
- Setup also writes an AGENTS.md file in the invoking project, changing the instructions an AI agent may follow.
- This configuration work runs through the explicit `npm run setup` command, not automatically on import or install.
- The postinstall script only creates an initial `.state/workflow-state.json` file when one does not already exist.
- The update checker is a separate command and is not run automatically by the MCP server.
Source & flagged code
10 flaggedPackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgFindings
Affected versions and remediation
This report applies to @programinglive/dev-workflow-mcp-server@1.17.1.
See all versions of @programinglive/dev-workflow-mcp-server for other recorded verdicts.
- Review the evidence and your use of @programinglive/dev-workflow-mcp-server@1.17.1 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.