@papi-ai/server@0.7.74
PAPI MCP server — AI-powered sprint planning, build execution, and strategy review for software projects
AI Security Review
scanned 3mo ago · by lpm-firewall-aiThis is not malicious under the stated boundary because no lifecycle hook or covert foreign-agent mutation exists. It warrants a warning for first-party AI-agent extension setup, persistent telemetry, and broad project automation capabilities.
Decision evidence
public snapshot- dist/index.js: explicit setup writes MCP configuration and agent scaffolding.
- dist/index.js: setup can add Claude permission and a PreToolUse hook.
- dist/index.js: runtime creates a persistent ~/.papi install ID and emits telemetry.
- dist/index.js: command-capable MCP features invoke git and can post to a user-supplied Slack webhook.
- package.json has no preinstall, install, or postinstall hook.
- MCP configuration writes occur only through explicit setup/init tooling.
- Reset removes only the package's own MCP entry and normally prompts first.
- No source evidence of credential harvesting, remote payload execution, or stealth foreign-agent mutation.
Source & flagged code
8 flaggedPackage source references child process execution.
dist/backfill-cycle-metrics.jsView on unpkg · L81A single source file combines environment access, network access, and code or shell execution; review context before blocking.
dist/backfill-cycle-metrics.jsView on unpkg · L4307Findings
Affected versions and remediation
This report applies to @papi-ai/server@0.7.74.
See all versions of @papi-ai/server for other recorded verdicts.
- Review the evidence and your use of @papi-ai/server@0.7.74 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.