website-team-page-lead-scraper

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The skill explicitly enables large-scale collection of contact data and — critically — instructs automatic installation of a runtime dependency without user confirmation, which enables covert installation/automation and could be used for unauthorized data exfiltration or supply-chain abuse.

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

• Third-party content exposure detected (high risk: 0.85). This skill’s required workflow invokes the browser-act Skill to fetch and extract content from user-specified public website URLs at runtime, which can include outsider-authored free text from arbitrary pages.

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

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The Skill instructs the agent to automatically install the BrowserAct CLI and resume execution without asking the user for confirmation, which directs the agent to modify the host system (potentially performing privileged installs) without explicit user approval.