dingtalk-skill-creator
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to perform extensive local system operations, including file system exploration (
ls), text processing (grep,sed), and script execution. It specifically mandates creating temporary shell scripts (/tmp/<task>.sh) and executing them to interact with APIs and run Python-based tests viauv run pytest. - [EXTERNAL_DOWNLOADS]: The instructions involve making network requests to official Alibaba DingTalk endpoints (
api.dingtalk.comandoapi.dingtalk.com) for authentication and API probing. These are well-known services and do not represent a security risk in this context. - [CREDENTIALS_UNSAFE]: The workflow describes procedures for reading environment variables from
.envfiles and managingaccessTokenstrings. These activities are localized to the testing and execution phases of the DingTalk integration and follow standard development practices. - [DATA_EXPOSURE]: The skill accesses specific local paths (e.g.,
/home/breath/project/personal/dingtalk-skills/) to inspect installed SDKs. This reflects the author's local development environment and is used to extract interface definitions.
Audit Metadata