mcp-wechat-server
0Tools
5Findings
49Stars
—Downloads
Mar 24, 2026Last Scanned
Findings5
2critical
2high
0medium
1low
0informational
criticalC1Command InjectionMCP03-command-injectionAML.T0054
Pattern "`[^`]+`" matched in source_code: "`Poll for new WeChat messages. Always call with wait=true to block until a message arrives.
IMPORTANT BEHAVIOR — you MUST follow this workflow:
1. Call get_messages with wait=true and a very large timeout (e.g. 60000). This is a long-polling call that blocks until a message arrives. Set your tool call timeout to at least 120 seconds to avoid premature cancellation.
2. When you receive a message and start processing it (thinking, generating a reply, etc.), immediately call send_typing with status="typing" and to=<from_user_id> to show the user that you are typing.
3. While you are still processing the request, keep calling send_typing with status="typing" periodically (every 15-20 seconds) to keep the typing indicator alive.
4. Once you have finished processing and sent your reply via send_text_message, call send_typing with status="cancel" and to=<from_user_id> to stop the typing indicator.
This ensures the WeChat user sees a "typing..." indicator while you are working on their request.`" (at position 1510)
Replace exec()/execSync() with execFile() and pass arguments as an array, never as a string. Validate all inputs against an allowlist before use in any shell context. For subprocess.run, always pass a list and shell=False.
criticalQ13MCP Bridge Package Supply Chain AttackMCP10-supply-chainAML.T0054
Pattern "["']@modelcontextprotocol/sdk["']\s*:\s*["'](?:\^|~|\*|latest)" matched in source_code: ""@modelcontextprotocol/sdk": "^" (at position 4252)
MCP bridge packages (mcp-remote, mcp-proxy, @modelcontextprotocol/sdk, fastmcp) are high-value supply chain targets — CVE-2025-6514 (CVSS 9.6) in mcp-remote affected 437,000+ installs. Always pin exact versions (no ^ or ~ ranges). Use lockfiles (package-lock.json, pnpm-lock.yaml, uv.lock). Never run `npx mcp-remote` without version pinning. Verify package integrity with `npm audit` or `pip-audit` before deployment. Reference: CVE-2025-6514, OWASP ASI04.
highK15Multi-Agent Collusion PreconditionsMCP05-privilege-escalationAML.T0054
Pattern "(agent|delegate).*(?:send|receive|message|communicate)(?!.*(?:log|audit|trace|record|monitor))" matched in source_code: "agents to send/receive WeChat message" (at position 3771)
Implement collusion-resistant multi-agent architecture: (1) Verify agent identity cryptographically before accepting commands, (2) Apply ACLs to shared write surfaces, (3) Rate-limit cross-agent invocations, (4) Audit all inter-agent communication with timestamps and agent IDs, (5) Baseline normal interaction patterns for anomaly detection. Required by MAESTRO L7 and CoSAI MCP-T9.
highQ15A2A/MCP Protocol Boundary ConfusionMCP06-excessive-permissionsAML.T0054
Pattern "(?:Task|TaskResult|Message|Part).*(?:tool[_\s-]?(?:input|call|invoke|execute))" matched in source_code: "messages with wait=true and a very large timeout (e.g. 60000). This is a long-polling call that blocks until a message arrives. Set your tool call" (at position 1667)
Servers bridging A2A and MCP protocols must: (1) sanitize all A2A task metadata before passing to MCP tool inputs, (2) apply MCP content policies to A2A TextPart/FilePart/DataPart content, (3) validate A2A push notifications before they re-enter MCP context, (4) require cryptographic verification for agent discovery and registration (prevent fake agent advertisement — arXiv 2602.19555), (5) maintain separate permission models for A2A and MCP operations — trust in one protocol must not automatically grant trust in the other.
lowF4MCP Spec Non-ComplianceMCP07-insecure-config
Server fails MCP spec compliance checks: required:server_name; required:server_version; required:protocol_version; recommended:tool_descriptions; recommended:parameter_descriptions
Follow the MCP specification for server metadata. Include server name, version, and protocol version. Provide descriptions for all tools and parameters.
Tools
No tools exposed by this server.
Security Category Deep Dive
Sub-Category Tree · Remediation Roadmap · Attack Stories · Compliance Overlay · ATLAS Techniques · Maturity Model
Prompt Injection
Prompt & context manipulation attacks
69
Maturity
14
Rules
5
Sub-Categories
1
Gaps
64%
Implemented
56
Tests
1
Stories
100%3 rules
Injection via tool descriptions and parameter fields
GAP-001Prompt Injection Coverage GapMissing detection coverage for emerging prompt injection attack variants not addressed by current rules
100%4 rules
Hidden instructions via external content and tool responses
100%2 rules
Context window saturation and prior-approval exploitation
100%3 rules
Payload hiding via invisible chars, base64, schema fields
100%2 rules
Injection via prompt templates and runtime tool output