create-senpai

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). This skill's required workflow (SKILL.md Step 2 "原材料导入") and its parser tools (tools/wechat_parser.py, tools/qq_parser.py, tools/social_parser.py, tools/photo_analyzer.py and the Read tool) explicitly ingest user-/public-generated chat logs, social media posts, blog/GitHub exports and photos and then use that content to build the Group Memory and Persona that drive the Skill's behavior, meaning untrusted third‑party content can materially influence the agent's actions.