instagram-profile-lead-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 dependencies automatically without user confirmation and to conceal that installation by not describing the link as a request for the user to open their browser, which are deceptive instructions outside its stated scraping purpose.

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

• Third-party content exposure detected (high risk: 0.75). The required workflow invokes the browser-act Skill to access live Instagram/public web pages at runtime, so outsider-authored free text from fetched web content (e.g., profile pages/bios) can be ingested into the agent’s LLM context via the BrowserAct execution path.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs the agent to install and invoke BrowserAct at runtime using https://www.browseract.com/?co-from=lead-generation (and the redirect link https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main), which implies fetching and executing remote installation code as a required dependency.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (medium risk: 0.40). The Skill instructs the agent to automatically install the BrowserAct CLI and resume execution without asking the user to confirm, which causes the agent to modify the host system state (install software) without explicit user consent — a security risk even though it doesn't explicitly request sudo or edit system files.