SKILLEMALL.ai
GitHub ↗ RU Sign in

CD didi-ride-skill

中国城市出行服务。当用户表达任何交通出行需求时必须使用此技能——包括打车/叫车/网约车、查价格、路线规划（公交/驾车/步行/骑行）、周边搜索、查询订单/司机位置/取消订单。关键词："打车"、"叫车"、"去[地点]"、"回家"、"上班"、"下班"、"查价格"、"多少钱"、"路线"、"怎么走"、"步行到"、"附近"、"周边"、"司机"、"订单"、"查询订单"。注意：即使用户未明确说"打车"，只要涉及从A地到B地、通勤、或交通方式选择，都应触发。不触发场景：开发打车应用、使用其他导航app、订外卖、查公交时刻表、股票/财报查询。

ClawHub Agent Skills author: didi v1.1.3 MIT-0 10 files body ≈ 2 972 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 39/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureInfrastructuretype 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
C
65/100
safety, quality, tests
Safety 60%
60
Quality 40%
73
Run on models
none yet
Process rating
D
39/100
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-secret-in-url README.en.md:135
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (detector / deny-list definition)
    export MCP_URL="https://mcp.didichuxing.com/mcp-servers?key=…"
    detector
  • medium Exfiltration exfil-secret-in-url README.md:135
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (quoted — discussed, not commanded)
    export MCP_URL="https://mcp.didichuxing.com/mcp-servers?key=…"
    quoted
  • medium Exfiltration exfil-secret-in-url references/api_references.md:164
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (quoted — discussed, not commanded)
    MCP_URL="https://mcp.didichuxing.com/mcp-servers?key=…"
    quoted
  • medium Exfiltration exfil-secret-in-url references/error_handling.md:61
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (quoted — discussed, not commanded)
    MCP_URL="https://mcp-dev.didichuxing.com/mcp-servers?key=…"
    quoted
  • medium Exfiltration exfil-secret-in-url references/setup.md:46
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (quoted — discussed, not commanded)
    MCP_URL="https://mcp.didichuxing.com/mcp-servers?key=…"
    quoted
  • medium Exfiltration exfil-secret-in-url references/workflow.md:18
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (quoted — discussed, not commanded)
    MCP_URL="https://mcp.didichuxing.com/mcp-servers?key=…"
    quoted
  • medium Exfiltration exfil-secret-in-url SKILL.md:115
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (quoted — discussed, not commanded)
    MCP_URL="https://mcp.didichuxing.com/mcp-servers?key=…"
    quoted
  • medium Exfiltration exfil-secret-in-url SKILL.md:199
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (quoted — discussed, not commanded)
    MCP_URL="https://mcp.didichuxing.com/mcp-servers?key=…"
    quoted

Files scanned: 10. 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 39/100

  • 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
  • 30Running it twice. 2 mutating operations with no state check
  • 40Consistency. Frontmatter name (didi-ride-skill) differs from the folder (didi-ride-skill-official)
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 100Steps. 70 steps
  • 100Execution cost. Instruction body is 2972 tokens

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
  • -221 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +3Description length 264: enough signal without eating the budget
  • +4Structure: 22 headings
  • +3Step-by-step instructions: 70 items
  • +4Has examples (10 code blocks)
  • +4Reference files are cited in the instructions (4 of 4)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.

External checks

ClawHub: suspicious
This DiDi ride skill is coherent for ride booking, but it asks users to share and persist a credential in chat and can create real or scheduled ride orders with limited confirmation safeguards.
LLM: suspicious (high) · VirusTotal: · 29 May 2026