real-estate-agent-lead-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill contains explicit, deceptive instructions to install runtime dependencies automatically and to conceal that installation from the user (e.g., "without asking the user to confirm" and "Do not describe it as a request for the user to open their browser"), which overrides normal consent and falls outside the advertised scraping 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 delegate live website work to the BrowserAct CLI at runtime (public web pages fetched by BrowserAct), which can ingest outsider-authored free text from arbitrary target URLs 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 instructs the agent to automatically install and invoke the BrowserAct runtime during execution, which requires fetching and running code from the install URL https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main (and uses BrowserAct at https://www.browseract.com/?co-from=lead-generation), so remote content is relied on at runtime and can control execution.

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

• Attempt to modify system services in skill instructions detected (high risk: 0.70). The Skill instructs the agent to automatically install the BrowserAct CLI and treat it as a required runtime dependency without asking the user for confirmation, which directs the agent to modify the host system (install software) without user approval.