@programinglive/dev-workflow-mcp-server@1.12.1
MCP server to enforce development workflow discipline
AI Security Review
scanned 7d ago · by lpm-firewall-aiThe project-wide agent instruction write occurs only through the explicit setup command and matches the package’s stated workflow-enforcement purpose. Because it changes broader agent instructions, classify it as a warning-level agent capability risk.
Decision evidence
public snapshot- The explicit setup command writes a project-root AGENTS.md when one is absent.
- The generated AGENTS.md directs coding agents to use this package’s mandatory workflow tools.
- The postinstall hook creates only a .state/workflow-state.json file in the invoking project.
- The AGENTS.md write is performed by the separately named setup command, not by the postinstall hook.
Source & flagged code
9 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@1.12.1.
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@1.12.1 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.