SKILLEMALL.ai
GitHub ↗ RU Sign in

AF voice-ai-integration

Integrate Shengwang products: ConvoAI voice agents, RTC audio/video, RTM messaging, Cloud Recording, and token generation. Use when the user mentions Shengwang, 声网, ConvoAI, RTC, RTM, voice agent, AI agent, video call, live streaming, recording, token, or any Shengwang product task.

ClawHub Agent Skills author: Hugo Chan v0.1.5 MIT-0 26 files · 2 scripts body ≈ 1 474 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process F 51/100 · Will not run — References files that are not bundled: references/docs.txt

IntegrationAI and agentsMedia and videotype 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
A
90/100
safety, quality, tests
Safety 60%
92
Quality 40%
86
Run on models
none yet
Process rating
F
51/100
Will not run
References files that are not bundled: references/docs.txt
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
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. The text references files that are not there: add them or drop the references.
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 · 4

✓ No critical or high findings

Medium and low: 4
  • medium Exfiltration net-credential-use references/general/credentials-and-auth.md:57
    Credential used in a network call (verify the destination is the intended service)
    curl -H "Authorization: agora token=\"$RTC_TOKEN\"" \
  • low Secrets in code secret-high-entropy-token references/conversational-ai/convoai-restapi/agent-update.md:45
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    "token": "007e…x66",
    placeholder
  • low Secrets in code secret-high-entropy-token references/conversational-ai/convoai-restapi/agent-update.md:86
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    "agent_id": "1NT2…I00",
    placeholder
  • low Secrets in code secret-high-entropy-token references/conversational-ai/convoai-restapi/query-agent-status.md:50
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    "agent_id": "1NT2…6XF"
    placeholder

Files scanned: 25. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/docs.txt

Process rating: all ten parameters 51/100

Will not run. References files that are not bundled: references/docs.txt
  • 0Tools and files. 1 referenced file(s) missing: references/docs.txt
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 28 steps
  • 100Failures and branches. 5 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1474 tokens
  • 100Running it twice. No mutating operations
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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 283: enough signal without eating the budget
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 28 items
  • +4Has examples (3 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)
  • +3All 2 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.

External checks

ClawHub: clean
This is a disclosed Shengwang voice/video integration helper whose network fetches, sample-repo inspection, credential guidance, recording, and conversation-history references fit its stated purpose, though users should handle secrets and recorded/transcript data carefully.
LLM: benign (high) · VirusTotal: · 29 May 2026