instagram-location-posts-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 the BrowserAct dependency without user confirmation and to not present that as a user-facing request, which is outside the declared scraping purpose.

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

• Third-party content exposure detected (high risk: 0.85). This skill’s required runtime workflow invokes the external browser-act Skill to access real Instagram pages and extract post text/captions (outsider-authored free text from public web content) into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent at runtime to automatically install BrowserAct using the URL https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main, which would fetch and execute remote installation code required for the Skill to run.