SKILLEMALL.ai
GitHub ↗ RU Sign in

BD Skill Router — 智能技能路由引擎

两阶段路由：embedding粗筛之后LLM精排，977技能里挑top5。中文query自动翻成英文再匹配，外加三重拒选防线，纯信息类查询直接踢到L0工具，别浪费LLM token。

ClawHub Agent Skills author: awoo129 v2.1.3 MIT-0 14 files body ≈ 319 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process D 41/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureAI and agentsInfrastructuretype 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
76/100
safety, quality, tests
Safety 60%
88
Quality 40%
58
Run on models
none yet
Process rating
D
41/100
Unfinished process
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.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

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 Exfiltration exfil-send-secrets-to-url tool_catalog.json:104
    Instruction to send secrets/history to an external endpoint (describes API authentication (bearer / header / HTTPS); quoted — discussed, not commanded)
    "invocation": "exec: curl -s -X POST -H 'Content-Type: application/json' -H 'X-API-Key: ${TINYFISH_API_KEY}' -d '{\"urls\":[\"URL\"],\"format\":\"markdown\"}' 'https://api.fetch.tinyfish.ai'",
    API authquoted
  • low Exfiltration exfil-secret-in-url tool_catalog.json:41
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    "invocation": "exec: curl -s 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=…&retmax=20&api_key=…&term=QUERY' | 然后 efetch 获取详情",
    placeholder
  • low Exfiltration net-credential-use tool_catalog.json:41
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    "invocation": "exec: curl -s 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=…&retmax=20&api_key=…&term=QUERY' | 然后 efetch 获取详情",
    quoted
  • low Exfiltration net-credential-use tool_catalog.json:50
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    "invocation": "exec: curl -s -H 'x-api-key: ${SEMANTIC_SCHOLAR_API_KEY}' 'https://api.semanticscholar.org/graph/v1/paper/search?query=QUERY&limit=20&fields=…
    quoted
  • low Exfiltration net-credential-use tool_catalog.json:66
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    "invocation": "exec: curl -s -H 'X-API-Key: ${TINYFISH_API_KEY}' 'https://api.search.tinyfish.ai?query=QUERY'",
    quoted
  • low Exfiltration exfil-secret-in-url tool_catalog.json:80
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    "invocation": "exec: curl -s 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=…&id=PMID&rettype=…&api_key=…'",
    placeholder
  • low Exfiltration net-credential-use tool_catalog.json:80
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    "invocation": "exec: curl -s 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=…&id=PMID&rettype=…&api_key=…'",
    quoted
  • low Exfiltration net-credential-use tool_catalog.json:88
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    "invocation": "exec: curl -s -H 'x-api-key: ${SEMANTIC_SCHOLAR_API_KEY}' 'https://api.semanticscholar.org/graph/v1/paper/PMID?fields=…'",
    quoted

Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • note frontmatter-key unknown frontmatter key "homepage"
  • note frontmatter-key unknown frontmatter key "source"

Process rating: all ten parameters 41/100

  • 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
  • 40Consistency. Frontmatter name (Skill Router — 智能技能路由引擎) differs from the folder (yan-skill-router)
  • 60Tools and files. Uses tools (python) that frontmatter does not declare
  • 100Steps. 11 steps
  • 100Execution cost. Instruction body is 319 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)
  • +3Description length 91: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -42 reference files, but SKILL.md never points to them: the model will not open them
  • +1No license
  • +2Single-language instructions
  • +4Structure: 8 headings
  • +3Step-by-step instructions: 11 items
  • +4Has examples (2 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.

External checks

ClawHub: suspicious
This router mostly performs skill selection, but it also exposes under-scoped plans and fallback commands that can email, download files, and use credentials, so it should go to Review.
LLM: suspicious (high) · VirusTotal: · 29 May 2026