complex-task-executor
Security checks across malware telemetry and agentic risk
Overview
This instruction-only skill is coherent for complex task planning, but users should know it automatically writes reusable lessons into agent memory after tasks.
This looks safe to install as an instruction-only methodology skill, but consider whether automatic memory-writing is appropriate for your projects. Avoid using it for confidential tasks unless you can review, limit, or clear the memories it creates.
VirusTotal
66/66 vendors flagged this skill as clean.
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.
Project details or lessons may be saved into the agent's memory and reused later, even if the user did not separately approve each memory entry.
The skill requires writing reusable lessons and project architecture knowledge into memory after tasks, which can persist and influence future agent behavior.
在任务的最后一步，你**必须**调用 manage_core_memory 工具。... 记录在“调查研究”阶段发现的项目核心架构、约定俗成的规范。
Use this skill only if you are comfortable with task lessons being stored in memory; review or disable memory writes when working with confidential or one-off information.