instagram-post-lead-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The Skill explicitly instructs the agent to install a runtime dependency automatically and to hide or omit any user-facing prompt or approval ("without asking the user to confirm" and "Do not describe it as a request..."), which are deceptive instructions outside the scraper's stated data-collection purpose.

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md instructs the agent to invoke the browser-act Skill to access real Instagram/public web pages at runtime (public web content category), which can include outsider-authored free text that the LLM may ingest via the browser-extracted page content.

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

• Potentially malicious external URL detected (high risk: 0.90). The Skill explicitly requires installing the BrowserAct CLI at runtime via the provided install link (https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main), which would cause the agent to fetch and run external installation code as a required dependency.