SKILLEMALL.ai
GitHub ↗ RU Sign in

FC tcm-prescription-api

中医药方剂API查询技能。通过HTTP API查询中医药方剂数据库中的方剂资料。支持方剂搜索、方剂详情查看、分类浏览、症状推荐等功能。This skill should be used when the user mentions: 查方剂、搜索方剂、方剂详情、中药方、方剂分类、症状推荐方剂、中医药方查询、方剂数据、prescription search、herb formula、TCM prescription、查询中药、方剂API、方剂数据库。

Blockedguard blocked the skill: signs of malicious behaviour
ClawHub Agent Skills author: Phal studio v1.0.6 MIT-0 5 files · 1 script body ≈ 942 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches

IntegrationInfrastructuretype 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
F
37/100
safety, quality, tests
Safety 60%
0
Quality 40%
92
Run on models
none yet
Process rating
C
52/100
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
Guard blocked this skill: critical findings below. Do not install it until the author fixes them.

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Exfiltration
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. Remove the critical guard findings (secrets, dangerous commands, hidden instructions): while they stand the skill is blocked and cannot grade above F.
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 · 6

  • critical Exfiltration exfil-secret-in-url-exfil-host references/api-reference.md:33
    Credential sent in a URL query string to a known exfiltration host (quoted — discussed, not commanded)
    curl -s "https://119.91.226.122/api/api-keys/status?key=…"
    quoted
  • critical Exfiltration exfil-secret-in-url-exfil-host references/api-reference.md:239
    Credential sent in a URL query string to a known exfiltration host (quoted — discussed, not commanded)
    curl -s "https://119.91.226.122/api/api-keys/status?key=…"
    quoted
Medium and low: 4
  • medium Exfiltration net-credential-use references/api-reference.md:33
    Credential used in a network call (verify the destination is the intended service)
    curl -s "https://119.91.226.122/api/api-keys/status?key=…"
  • medium Exfiltration net-credential-use references/api-reference.md:239
    Credential used in a network call (verify the destination is the intended service)
    curl -s "https://119.91.226.122/api/api-keys/status?key=…"
  • medium Exfiltration net-credential-use scripts/query_prescriptions.sh:39
    Credential used in a network call (verify the destination is the intended service)
    curl -s "$url" -H "X-API-Key: $API_KEY" | python3 -m json.tool
  • medium Exfiltration net-credential-use scripts/query_prescriptions.sh:57
    Credential used in a network call (verify the destination is the intended service)
    curl -s "${API_BASE}/prescriptions/${id}" -H "X-API-Key: $API_KEY" | python3 -m json.tool

Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

✓ No remarks against the Agent Skills spec

Process rating: all ten parameters 52/100

  • 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
  • 60Tools and files. Uses tools (web, python) that frontmatter does not declare
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 33 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 942 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
  • +2Single-language instructions
  • +3Description length 226: enough signal without eating the budget
  • +4Structure: 22 headings
  • +3Step-by-step instructions: 33 items
  • +4Has examples (6 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)
  • +3All 1 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.

External checks

ClawHub: suspicious
This prescription-search skill appears purpose-aligned, but it sends health-related symptom text to a raw-IP external service and documents unsafe API-key-in-URL flows.
LLM: suspicious (medium) · VirusTotal: · 29 May 2026