SKILLEMALL.ai
GitHub ↗ RU Sign in

BC huo15-openclaw-wechat-service

OpenClaw 微信服务号（公众号）渠道插件 v2.3.5 hotfix —— **修 errcode 45002 content size out of limit**：truncateForWechatText 改字节截断（微信限 2048 字节不是字符，中文 1 字 = 3 字节），默认 1900 字节留余量；保护 <a href> 标签不截在内部避免 XML 错乱；中文 / emoji / 混合场景全覆盖。症状：v2.3.0~v2.3.4 粉丝只收 placeholder 不收 LLM 真回复——根因 LLM 输出 > 600 中文字超 2048 字节被微信拒。承袭 v2.3.x 全部能力。287 vitest 用例全过。

ClawHub Agent Skills author: Job Zhao v2.3.5 MIT-0 80 files · 1 script body ≈ 586 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
80/100
safety, quality, tests
Safety 60%
88
Quality 40%
68
Run on models
none yet
Process rating
C
53/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Obfuscation medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 8

✓ No critical or high findings

Medium and low: 8
  • medium Obfuscation uni-zero-width src/shared/markdown-to-wechat.ts:20
    Zero-width / invisible characters (possible hidden text) (3 occurrences)
    const ZERO_WIDTH = /[␀-␀␀]/g;
  • low Secrets in code secret-high-entropy-token package-lock.json:156
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…wIN//F77/IADDSs58i+MDaO…jeo+YFg==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:369
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…XIB+FGku…WvF/QqOVWvJtWVYaLddANJ+aUklVr2ieuw==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:451
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha5…0SL+9JeP…120+zA0O…dw2+iw==",
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:486
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…RAu+EGHG…L8i+zXBl…44B/Kom4…sXQ==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:811
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…5HY+AxRz…Lsf+l721…TaW/BwghSwQhGgoNgrxMw==",
    detector
  • low Secrets in code secret-high-entropy-token README.md:500
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "id": "wech…123",
    quoted
  • low Secrets in code secret-high-entropy-token src/shared/authorization.test.ts:70
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; test fixture / example file)
    expect(extractOpenidFromAgentId("wech…123", "default")).toBe(
    detectorfixture

Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 53/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 100Tools and files. No external tools needed
  • 100Steps. 6 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 586 tokens
  • 100Running it twice. No mutating operations

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -31 of 1 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 320: enough signal without eating the budget
  • +4Structure: 11 headings
  • +3Step-by-step instructions: 6 items
  • +4Has examples (4 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.

External checks

ClawHub: suspicious
This appears to be a real WeChat service-account plugin, but it grants broad account-control powers by default and can persist or sync chat transcripts, so it needs careful review before use.
LLM: suspicious (high) · VirusTotal: · 29 May 2026