account-intelligence

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified during the analysis.\n- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill implements privacy-preserving measures for contact data, including name masking (initials only), domain-only email display, and phone number masking.\n- [EXTERNAL_DOWNLOADS]: Fetches templates and guidelines from Lusha's official documentation site (lusha.com), which is a well-known service provider.\n- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection through external data ingestion.\n
  • Ingestion points: Research context and account identifiers provided via $ARGUMENTS in SKILL.md, and external account data retrieved via Lusha tool calls.\n
  • Boundary markers: The skill does not use explicit delimiters or instructions to ignore embedded commands in the retrieved data.\n
  • Capability inventory: The skill's capabilities are limited to read-only research tool calls; it does not have file-writing or code execution permissions.\n
  • Sanitization: There is no evidence of sanitization or filtering of the retrieved account data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 11:07 AM
Security Audit — agent-trust-hub — account-intelligence