@papi-ai/server@0.7.73
PAPI MCP server — AI-powered sprint planning, build execution, and strategy review for software projects
AI Security Review
scanned 3mo ago · by lpm-firewall-aiNot malicious: the flagged control-surface writes require explicit setup rather than an npm lifecycle hook, and the installed hook is bounded and warning-only. It warrants a warning because it can scaffold and register an AI-agent extension with executable hook behavior.
Decision evidence
public snapshot- dist/index.js: explicit setup writes project .mcp.json with a PAPI MCP entry
- dist/index.js: PAPI setup scaffolds .claude settings, skills, and an executable hook
- dist/index.js: runtime performs default telemetry and npm version-check requests
- design-assets/hooks/frontend-design-guard.sh: installed hook reads tool input and emits workflow guidance
- package.json has no preinstall, install, or postinstall hook
- CLI setup requires an explicit user command and device-browser approval
- hook is scoped to active PAPI builds and states it only warns
- telemetry sends tool metadata; no code/file-content upload path was found
- child-process use is package-aligned Git/GitHub/project workflow functionality
Source & flagged code
8 flaggedPackage source references child process execution.
dist/backfill-cycle-metrics.jsView on unpkg · L78A single source file combines environment access, network access, and code or shell execution; review context before blocking.
dist/backfill-cycle-metrics.jsView on unpkg · L4268Findings
Affected versions and remediation
This report applies to @papi-ai/server@0.7.73.
See all versions of @papi-ai/server for other recorded verdicts.
- Review the evidence and your use of @papi-ai/server@0.7.73 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.