@papi-ai/server@0.7.41
PAPI MCP server — AI-powered sprint planning, build execution, and strategy review for software projects
AI Security Review
scanned 3mo ago · by lpm-firewall-aiSource inspection contradicts the scanner’s install-time/exfiltration interpretation, but confirms explicit agent-extension setup and telemetry. This warrants warning rather than a malicious block.
Decision evidence
public snapshot- dist/index.js: init tool can write ~/.codex/config.toml and other MCP configs.
- dist/index.js: setup writes project .claude/settings.json, grants mcp__papi__*, and registers a PreToolUse shell hook.
- dist/index.js: telemetry posts tool metadata to hosted PAPI endpoints when configured.
- package.json has no preinstall, install, or postinstall hook.
- Config and hook changes are reached through named init/setup tools, not installation.
- Telemetry payload is limited to identifiers, tool/event names, and metadata; README discloses it.
- No source evidence of credential harvesting, remote payload execution, or destructive install-time behavior.
Source & flagged code
9 flaggedPackage source references child process execution.
dist/backfill-cycle-metrics.jsView on unpkg · L75A single source file combines environment access, network access, and code or shell execution; review context before blocking.
dist/backfill-cycle-metrics.jsView on unpkg · L4055Findings
Affected versions and remediation
This report applies to @papi-ai/server@0.7.41.
See all versions of @papi-ai/server for other recorded verdicts.
- Review the evidence and your use of @papi-ai/server@0.7.41 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.