Workflow Decomposer

工作流任务拆解与模型编排技能。使用场景：(1) 收到复杂工作任务需要拆解为可执行步骤，(2) 需要为不同步骤选择最合适的模型，(3) 需要跟踪工作流进度和模型使用情况，(4) 长时间任务卡住需要问题诊断和解决方案。

This skill appears coherent and non-malicious, but review these before installing: (1) it writes state files (workflow-state.json or workspace/memory/workflow-state.json) to your agent/workspace — if you need to avoid writes run it in an isolated workspace or inspect/redirect those paths; (2) the skill prefers Alibaba Qwen models in its templates — ensure the runtime has those models available or edit templates to target models you trust; (3) documentation mentions auto-triggering and web_fetch capabilities but there is no install-time trigger or network integration in the bundle — if you expect automatic background runs or network fetches, verify the runtime behavior; (4) no secrets or external URLs are requested by the skill. If you want higher assurance, open and read the two Python scripts (they are short) and confirm the file paths used are acceptable, or run them in a sandboxed environment. If the publisher or homepage are unknown and you require provenance, prefer skills with a known source or more metadata.

Type: OpenClaw Skill Name: workflow-decomposer Version: 1.0.0 The skill bundle's core functionality and documentation are benign, focusing on workflow decomposition and model orchestration. However, the `scripts/progress-tracker.py` file contains a vulnerability: it uses `json.loads(sys.argv[4])` to parse step data directly from command-line arguments without explicit input validation. While not indicative of malicious intent, this lack of input sanitization could allow an attacker (or a compromised agent) to supply malformed or excessively large JSON, potentially leading to a denial-of-service for the script or the agent process due to resource exhaustion during parsing. This constitutes a vulnerability, classifying the skill as 'suspicious' rather than 'benign' under the given criteria.