instagram-comment-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The skill contains explicit deceptive instructions to auto-install a dependency without user confirmation and to hide/omit describing the installation request, which is outside the stated scraping purpose and user-transparent behavior.

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 invoke the browser-act Skill to access real Instagram pages at runtime and extract comment text (outsider-authored free text from public/authorized Instagram content) into the agent’s context for processing.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly treats the BrowserAct CLI as a required runtime dependency and directs the agent to automatically install it via the Install BrowserAct link (https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main), which would fetch and run external installation code at runtime.