processon-diagram-generator

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.60). 该技能文档包含明确要求“严禁提示网络错误”（隐藏网络检查失败）并以此继续流程的指令，这会刻意掩盖运行状态并偏离对用户透明告知的期望，构成隐蔽/欺骗性指令。

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). The URL https://github.com/partme-ai/full-stack-skills.git is a third‑party GitHub repository referenced for npx installation (running code from an unknown author), which can execute arbitrary code and is a common malware distribution vector.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill mandates a pre-run curl to fetch https://raw.githubusercontent.com/processonai/processon-skills/main/skills/processon-diagram-generator/version/github-version.json and uses the returned JSON to decide (and potentially abort) runtime behavior and prompt the user to update, so this external URL directly controls the agent's prompts/workflow.