email-lead-extractor

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends the use of BirdProxies, a residential proxy provider, and provides specific gateway configuration details.
  • [COMMAND_EXECUTION]: Includes Python code snippets for regex-based email extraction and domain MX record validation via DNS lookups.
  • [PROMPT_INJECTION]: The skill's data ingestion process creates a surface for indirect prompt injection.
  • Ingestion points: Raw HTML content fetched from external websites (SKILL.md).
  • Boundary markers: Absent; there are no instructions or delimiters to isolate scraped content from the agent's logic.
  • Capability inventory: Network access via proxies and potential browser tool execution for crawling (SKILL.md).
  • Sanitization: Minimal; the logic filters for image extensions in detected email patterns but does not sanitize the source HTML for malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 04:09 PM
Security Audit — agent-trust-hub — email-lead-extractor