Volcengine Ai Text Ark Chat

Text generation and chat completion on Volcengine ARK. Use when users need long-form writing, summarization, extraction, rewriting, Q&A, or prompt optimization with ARK text models.

Security Scan

The skill's instructions largely match a Volcengine ARK chat integration, but it references an undeclared API credential and a suspicious-looking endpoint hostname, which are incoherent and could lead to unintended key exposure.

Purpose & Capability

Name/description and the request template align with a Volcengine ARK text/chat integration. However, the SKILL.md expects an ARK_API_KEY and endpoint/region even though the skill metadata declares no required environment variables — that mismatch is unexplained.

Instruction Scope

Runtime instructions are mostly scoped to issuing ARK chat/completion calls and setting model params, which fits the purpose. But the checklist and example explicitly reference $ARK_API_KEY (an environment secret) even though that secret is not declared in the skill metadata. The cURL example posts to an external endpoint (see below) — the instructions will cause the agent to transmit user-provided data and any ARK_API_KEY to that endpoint.

Install Mechanism

Instruction-only skill with no install steps and no code files. This is low-risk from an install perspective — nothing is written to disk by the skill itself.

Credentials

The SKILL.md requires an API key (ARK_API_KEY) to function, but the registry metadata lists no required env vars or primary credential. That omission is a mismatch: a user should expect to provide a secret for this integration, and the metadata should declare it. Requiring an API key is reasonable for this type of skill, but the lack of explicit declaration is a transparency/ownership problem.

Persistence & Privilege

always is false and the skill has no install or background components. It does not request persistent system privileges or modify other skill configs.

What to consider before installing

This skill appears to be a simple Volcengine ARK chat wrapper, but there are two things you should resolve before installing: (1) SKILL.md uses $ARK_API_KEY but the skill metadata does not declare any required environment variables — confirm the skill will require and store your ARK_API_KEY and that you are comfortable providing it. (2) The example endpoint URL (ark.cn-beijing.volces.com) looks off compared to Volcengine's known domains; verify the endpoint hostname is correct and points to the official Volcengine service (a wrong hostname could route your API key and data to an unintended server). If you can't verify those two items, treat the skill as untrusted or run it in a restricted/test environment with a limited API key. Also ask the publisher to update the metadata to explicitly list required env vars (ARK_API_KEY, any endpoint/region settings) and to correct/confirm the endpoint domain.

Execute text/chat tasks on Volcengine ARK with stable parameter defaults and reproducible request templates.

Execution Checklist

1. Verify ARK_API_KEY, endpoint ID, and region.
2. Clarify task type (chat, summarize, rewrite, extract).
3. Set safe defaults (temperature, max_tokens, top_p).
4. Return output plus key parameters used.

Minimal Request Template

curl https://ark.cn-beijing.volces.com/api/v3/chat/completions \
  -H "Authorization: Bearer $ARK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ep-xxxx",
    "messages": [{"role":"user","content":"请总结这段文本"}],
    "temperature": 0.2
  }'

References

• references/sources.md