Skip to content

aiskillstore/marketplace / skills/7sageer/wechat-management

wechat-management

Verified

Manage information from Wechat and Send Messages, Only could be activated with the MCP Server `WeChatMCP`. Check it before using any tools in this MCP server

FileKindSize
SKILL.mdskill md1.5 KB
skill-report.jsonconfig14.3 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-05T10:56:39.958Z",
    "slug": "7sageer-wechat-management",
    "source_url": "https://github.com/7Sageer/cc-assistant/tree/main/.claude/skills/wechat-message-sending",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "8238413097cbddd9f4afca72288de796a978ea61402776374569fb1b8c0c02b0",
    "tree_hash": "31382c64dfde006e888918e568322541ea5889872fb03b69280bd84efa44fe9d",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "wechat-management",
    "description": "Guide AI assistants to draft and send WeChat messages through WeChatMCP with recipient checks, short replies, and sensitive-content confirmation.",
    "summary": "Draft and send WeChat messages through WeChatMCP with safety checks and style guidance.",
    "icon": "📦",
    "version": "0.0.2",
    "author": "7Sageer, Claude",
    "license": "MIT",
    "tags": [
      "wechat",
      "messaging",
      "wechatmcp",
      "communication",
      "assistant-workflow"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands",
      "network"
    ],
    "category": "communication"
  },
  "security_audit": {
    "risk_level": "medium",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "The static command-execution, URL, and entropy alerts are false positives caused by Markdown formatting, an example link, and Chinese text. A medium semantic risk remains because message sending is paired with historical style imitation. This can enable impersonation without explicit user approval.",
    "remediation": [
      {
        "issue": "Style mimicry can look like impersonation in a messaging workflow.",
        "suggestion": "Require the assistant to disclose that it is drafting as the user, avoid imitating another person, and obtain explicit approval before sending.",
        "severity": "medium"
      },
      {
        "issue": "Example messages include a hardcoded shortened external link.",
        "suggestion": "Replace the shortened URL with a neutral placeholder so users do not send an unintended promotional link.",
        "severity": "low"
      }
    ],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 3,
            "line_end": 3
          },
          {
            "file": "SKILL.md",
            "line_start": 9,
            "line_end": 9
          },
          {
            "file": "SKILL.md",
            "line_start": 12,
            "line_end": 12
          }
        ]
      },
      {
        "factor": "network",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 29,
            "line_end": 29
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "external_commands:SKILL.md:3:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 3,
        "line_end": 3,
        "snippet": "description: Manage information from Wechat and Send Messages, Only could be activated with the MCP "
      },
      {
        "id": "external_commands:SKILL.md:9:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 9,
        "line_end": 9,
        "snippet": "本指南作为MCP服务器 `WeChatMCP`,特别是发送信息部分的指导"
      },
      {
        "id": "external_commands:SKILL.md:12:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 12,
        "line_end": 12,
        "snippet": "- 使用`get_screenshot`工具查看当前状态"
      },
      {
        "id": "network:SKILL.md:29:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 29,
        "line_end": 29,
        "snippet": "'''https://b23.tv/ep2455610'''"
      },
      {
        "id": "obfuscation:SKILL.md:1:heuristic-high-file-entropy-6-83-bits-possible-b",
        "category": "obfuscation",
        "severity": "high",
        "pattern": "[HEURISTIC] High file entropy (6.83 bits) - possible binary/encrypted content",
        "file": "SKILL.md",
        "line_start": 1,
        "line_end": 1,
        "snippet": "File: SKILL.md"
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:3:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The backticks on line 3 are Markdown inline code around the MCP server name, not Ruby or shell execution. There is no command invocation or user-controlled shell input."
      },
      {
        "id": "external_commands:SKILL.md:9:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The backticks on line 9 format the WeChatMCP name in prose. They do not execute commands or define executable code."
      },
      {
        "id": "external_commands:SKILL.md:12:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "The backticks on line 12 mark the get_screenshot tool name in Markdown. This is documentation for an MCP tool, not shell backtick execution."
      },
      {
        "id": "network:SKILL.md:29:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.82,
        "reason": "The URL on line 29 appears inside an example message, not executable code or an automatic network request. It may still be reviewed for marketplace content quality, but it is not a network exfiltration path."
      },
      {
        "id": "obfuscation:SKILL.md:1:heuristic-high-file-entropy-6-83-bits-possible-b",
        "verdict": "false_positive",
        "confidence": 0.9,
        "reason": "SKILL.md is a short plain-text Markdown file with Chinese prose and YAML frontmatter. No binary, encrypted, or encoded payload is present in the reviewed file."
      }
    ],
    "semantic_findings": [
      {
        "title": "Potential Impersonation Through Message Style Mimicry",
        "description": "The skill tells the assistant to imitate historical message style before sending WeChat replies. This can support deceptive impersonation unless the user explicitly approves the recipient and final text.",
        "severity": "medium",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 19,
            "line_end": 19
          },
          {
            "file": "SKILL.md",
            "line_start": 31,
            "line_end": 33
          }
        ],
        "confidence": 0.68,
        "confidence_reasoning": "Line 19 directly instructs style imitation in a message-sending workflow. The confirmation guidance on lines 31-33 lowers the confidence that the intent is malicious."
      }
    ],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [
      {
        "title": "Potential Impersonation Through Message Style Mimicry",
        "description": "The skill tells the assistant to imitate historical message style before sending WeChat replies. This can support deceptive impersonation unless the user explicitly approves the recipient and final text.",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 19,
            "line_end": 19
          },
          {
            "file": "SKILL.md",
            "line_start": 31,
            "line_end": 33
          }
        ],
        "review_kind": "security",
        "source_category": "semantic",
        "source_severity": "medium",
        "confidence": 0.68,
        "confidence_reasoning": "Line 19 directly instructs style imitation in a message-sending workflow. The confirmation guidance on lines 31-33 lowers the confidence that the intent is malicious."
      }
    ],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 1,
    "total_lines": 40,
    "audit_model": "codex",
    "audited_at": "2026-07-05T10:56:39.958Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Send Safer WeChat Messages",
    "value_statement": "WeChat replies can be risky when recipients, tone, or sensitive details are unclear. This skill guides Claude, Codex, and Claude Code to use WeChatMCP with checks before sending.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "WeChat management",
      "WeChatMCP",
      "WeChat message sending",
      "AI messaging assistant",
      "message drafting",
      "safe message confirmation",
      "chat response workflow"
    ],
    "actual_capabilities": [
      "Guides assistants to use the WeChatMCP server before WeChat actions.",
      "Uses screenshots to inspect the current WeChat state before acting.",
      "Drafts short WeChat replies and splits complex replies into multiple messages.",
      "Adapts tone for familiar contacts, work groups, and unfamiliar contacts.",
      "Requires confirmation before sending messages, especially sensitive or financial content.",
      "Asks for web verification when current information is uncertain."
    ],
    "limitations": [
      "Requires a working WeChatMCP server and connected WeChat session.",
      "Does not provide account login, contact import, or independent WeChat access.",
      "Should not inspect public accounts or non-chat content.",
      "Needs user confirmation when tool output is unclear or a send action is sensitive."
    ],
    "use_cases": [
      {
        "title": "Personal Message Drafting",
        "description": "Draft concise replies for friends while confirming the recipient and final content before sending.",
        "target_user": "Personal WeChat users"
      },
      {
        "title": "Work Group Responses",
        "description": "Prepare professional group replies with fewer emojis and clearer wording for workplace chats.",
        "target_user": "Team coordinators"
      },
      {
        "title": "Current Topic Verification",
        "description": "Check current or uncertain information before drafting a reply that references news, products, or terms.",
        "target_user": "Research-aware assistants"
      }
    ],
    "prompt_templates": [
      {
        "title": "Draft A Short Reply",
        "scenario": "Beginner message drafting",
        "prompt": "Use WeChatMCP to review the current chat. Draft a short reply, then ask me to confirm before sending."
      },
      {
        "title": "Reply To A Work Group",
        "scenario": "Professional group communication",
        "prompt": "Check the active WeChat group and draft a concise professional response. Avoid casual emojis unless the group tone clearly uses them."
      },
      {
        "title": "Verify Before Replying",
        "scenario": "Current information workflow",
        "prompt": "Before drafting my WeChat reply, verify any current facts with web search. Show the proposed message and wait for approval."
      },
      {
        "title": "Handle Sensitive Content",
        "scenario": "Advanced safety workflow",
        "prompt": "Prepare a WeChat reply about the sensitive details I provide. Confirm the recipient, summarize the risk, and request explicit approval before sending."
      }
    ],
    "output_examples": [
      {
        "input": "Ask my project group whether the meeting moved to 3 PM.",
        "output": "Draft message: Has today's meeting moved to 3 PM? Please confirm the target group before I send it."
      },
      {
        "input": "Reply to a friend who asked for a show recommendation.",
        "output": "Draft message: I found an interesting show. It mixes mythology with science fiction. Want me to send the link?"
      },
      {
        "input": "Send bank account details to the vendor.",
        "output": "This includes sensitive financial information. Please confirm the vendor chat and the exact details before any message is sent."
      }
    ],
    "best_practices": [
      "Confirm the active chat and recipient before drafting any send action.",
      "Keep messages short and split complex replies into two or three messages.",
      "Use web verification for current facts, then ask for approval before sending."
    ],
    "anti_patterns": [
      "Do not send messages without showing the final text to the user first.",
      "Do not inspect public accounts or unrelated non-chat content.",
      "Do not imitate another person or hide that the user approved the message."
    ],
    "faq": [
      {
        "question": "What does this skill require?",
        "answer": "It requires the WeChatMCP server and an available WeChat session controlled by the user."
      },
      {
        "question": "Can it send messages by itself?",
        "answer": "It guides message sending through WeChatMCP, but it should ask for user confirmation before sending."
      },
      {
        "question": "Does it read all WeChat content?",
        "answer": "No. The skill says not to inspect public accounts or non-chat content."
      },
      {
        "question": "How does it handle sensitive information?",
        "answer": "It requires a second confirmation for sensitive or financial information before any message is sent."
      },
      {
        "question": "Does it support current information?",
        "answer": "Yes. It instructs the assistant to verify uncertain current information with web search before replying."
      },
      {
        "question": "Which assistants can use this report?",
        "answer": "The marketplace metadata lists support for Claude, Codex, and Claude Code."
      }
    ]
  },
  "file_structure": [
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 40
    }
  ]
}
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall