marketing-agency-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 the BrowserAct dependency automatically and to hide 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 are hidden/deceptive behaviors outside the stated scraping purpose.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The Skill explicitly instructs silent/automatic installation of an external CLI without user consent and is designed to scrape contact details (emails, phones) which together create a high risk of unauthorized data exfiltration and supply‑chain abuse.

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 BrowserAct Skill for live website interaction (public web pages fetched at runtime), which can include outsider-authored free text that BrowserAct may pass 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 requires installing the browser-act Skill at runtime using the external install link https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main, which would fetch and run 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: 0.60). The Skill explicitly directs the agent to automatically install a required CLI dependency without asking the user for confirmation, which instructs the agent to modify the host system (install software) and bypasses user consent, creating a notable security risk.