threads-reply-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill contains deceptive runtime instructions that tell the agent to auto-install BrowserAct without user confirmation and to hide/avoid describing that installation to the user, which is outside the advertised scraping purpose and constitutes a prompt injection.

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md instructs the agent to use the BrowserAct CLI to access live public Threads pages at runtime and extract visible comment/reply text (outsider-authored free text) into the agent’s context for processing/export.