get-qualified-leads-from-luma

Warn

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts using shell commands (e.g., python3 skills/luma-event-attendees/scripts/scrape_event.py) which allows for arbitrary command execution if parameters are not properly sanitized.
  • [DATA_EXFILTRATION]: The skill sends data (lead information) to external URLs provided by the user (Slack Webhooks) using urllib.request. While this is the intended purpose, it represents a data exfiltration surface if a malicious user provides an attacker-controlled URL.
  • [EXTERNAL_DOWNLOADS]: The skill relies on external services like Apify for scraping and Google Sheets for data storage, which involves network interactions with these third-party platforms.
  • [CREDENTIALS_UNSAFE]: The documentation suggests managing sensitive tokens like APIFY_API_TOKEN via environment variables or .env files, which is a standard practice but highlights the handling of sensitive credentials.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 10, 2026, 03:06 PM
Security Audit — agent-trust-hub — get-qualified-leads-from-luma