email-finder
Warn
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: MEDIUMNO_CODECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [NO_CODE] (MEDIUM): The core implementation file 'scripts/find_emails.py' referenced in the documentation is missing from the skill payload. This prevents a complete security review of how the tool handles external data or system commands.
- [INDIRECT_PROMPT_INJECTION] (MEDIUM): The skill possesses a significant attack surface by ingesting untrusted data from external website pages (/contact, /about) and search engine results. Malicious actors could place hidden instructions on these pages to influence the AI agent's behavior during processing. Evidence: Ingestion points: homepage and subpages scraped via regex (find_emails.py); Capability inventory: network connections for HTTP, DNS, and SMTP; Boundary markers: absent in documentation; Sanitization: unknown due to missing source code.
- [COMMAND_EXECUTION] (LOW): The tool is designed to be invoked via shell commands (python3 scripts/find_emails.py), which is expected for this type of tool but requires that the agent properly sanitize inputs to prevent command injection.
- [EXTERNAL_DOWNLOADS] (LOW): The skill requires the installation of the 'dnspython' package from a third-party registry (PyPI).
Audit Metadata