Evaluation report

• Repository is reachable

  https://github.com/sinewaveai/agent-security-scanner-mcp @ ed8ea65 — ★ 111 · JavaScript · MIT · last push yesterday

• Manifest detected

  kind=mcp slug=agent-security-scanner-mcp · source=package.json

• Slug is URL-safe

  "agent-security-scanner-mcp" matches /^[a-z0-9][a-z0-9-]{0,62}$/

• Slug is unique within kind

  No collision found for mcp/agent-security-scanner-mcp

• Version is semver

  4.4.3

• Description quality

  36 words · 275 chars — "Security scanner MCP server for AI coding agents. Prompt injection firewall, pac…"

• README is present and substantial

  72,466 chars · 27 sections · 53 code blocks

• Tags / topics declared

  44 total — mcp, model-context-protocol, claude, opencode, kilocode, security (+38)

• README has usage / example sections

  found: Quick Start · Quick Start · Quick Start (+5)

• Homepage / docs URL declared

  https://www.proof-layer.com/

• Dependencies: known vulnerabilitieswarn

  3 high/critical advisories — @modelcontextprotocol/[email protected] (HIGH: GHSA-345p-7cg4-v4c7) · [email protected] (HIGH: GHSA-9ppj-qmqm-q256) (+1)

  Update the affected packages, then re-publish. (`npm audit` shows the same data locally.)

• LICENSE file at repo root

  LICENSE

• No sensitive files in the repo

  scanned for .env, credentials.json, *.pem, .ssh/, AWS / GCP configs — none found

• MCP: launch path

  bin: agent-security-scanner-mcp, cr-agent · scripts.start

• MCP: @modelcontextprotocol/sdk in dependencies

  pinned at "^1.25.3"

• MCP: SDK version pinned

  pinned at "^1.25.3"

• MCP: ESM package

  "type": "module"

• MCP: server surface

  0 tools

• Recent activity

  last push yesterday

• Tests detected

  5 test directories · 90 test files

• CI configuration detected

  GitHub Actions (4 workflows)

This artifact hasn't produced behavioral results yet: the evaluation sandbox couldn't run it (it may need credentials we don't provide, or a build our environment doesn't support). That's a limitation of our environment, not a verdict on the artifact.