ime_message_skill
Security checks across static analysis, malware telemetry, and agentic risk
Overview
The skill matches its stated text-polishing purpose and shows no malicious behavior, but it sends message text to a configured model service and requires a model API token.
Before installing, confirm you trust the configured model endpoint, set the API token securely, and remember that rewritten message text may be sent to the model provider. The artifacts also suggest keeping user review before sending messages, which is a good safety practice.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Any message text processed by the skill may be sent to the configured model provider.
The helper sends the user's original message text to an external OpenAI-compatible model service for rewriting. This is disclosed and central to the skill, but it means private chat text can leave the local environment.
client = OpenAI(api_key=api_key, base_url=base_url) ... {"role": "user", "content": build_user_prompt(original_text, rewrite_instruction)}Use the skill only with content you are comfortable sending to the configured provider, and verify the base URL and provider privacy terms before use.
A model-service credential is needed for the script to work, and mishandling that token could expose access to the model service.
The script requires a model API token, although registry requirements list no required environment variables or primary credential. The token use is purpose-aligned and disclosed in the documentation, but users should configure it carefully.
DEFAULT_API_KEY = os.environ.get("IME_MODEL_API_KEY", "") ... raise ValueError("缺少 API token，请设置 IME_MODEL_API_KEY 或通过 --api-key 传入")Store the token in a secret manager or environment variable, avoid hardcoding it, and avoid pasting it into chats or logs.
Users may need to install an external Python package before the helper works, and the exact package version is not fixed by the skill artifacts.
The helper depends on the OpenAI Python package, but the artifact set has no install spec or pinned dependency version. This is not suspicious by itself, but it is a provenance and reproducibility detail users should notice.
from openai import OpenAI ... raise SystemExit("缺少 openai 依赖，请先安装 openai：pip install openai")Install dependencies from trusted package sources and consider pinning a known-good OpenAI package version in your environment.