gmaps-leads

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the Bash tool to run Python orchestration scripts for lead scraping and enrichment.- [DATA_EXFILTRATION]: The skill manages sensitive Google OAuth credentials stored in token.json and credentials.json to facilitate syncing data with Google Sheets.- [EXTERNAL_DOWNLOADS]: The skill performs network requests to Apify's API and various third-party business websites to collect business data.- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface. * Ingestion points: Raw HTML and Markdown content is fetched from arbitrary external websites in scripts/extract_website_contacts.py. * Boundary markers: The prompt used for contact extraction via Claude lacks specific delimiters or instructions to ignore embedded commands. * Capability inventory: The skill operates in an environment with high-privilege access to shell commands and file system operations via Bash, Read, Write, and Edit. * Sanitization: Web content is converted to markdown but is not sanitized or filtered for malicious instructions before being passed to the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 12:42 AM
Security Audit — agent-trust-hub — gmaps-leads