instagram-post-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill explicitly instructs the agent to install a runtime dependency automatically and to hide or avoid requesting user approval (e.g., "without asking the user to confirm" and "Do not describe it as a request..."), which is a deceptive instruction that changes agent behavior beyond the scraping purpose.

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 Instagram pages/URLs at runtime (public web content), which can include outsider-authored free text like captions and comments that may be ingested into the 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 and invoke the BrowserAct CLI using the installer link https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main, which causes fetching and execution of remote installer code as a required dependency.