customer-health

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external tool outputs, which represents a potential injection surface.
  • Ingestion points: Customer account lists provided in $ARGUMENTS and external data retrieved via Lusha tool calls (intent signals, news, and hiring data).
  • Boundary markers: Not explicitly defined in the instructions.
  • Capability inventory: Tool invocations for searching companies and retrieving business signals. No arbitrary command execution or file system writes are present.
  • Sanitization: The skill includes a privacy rule to use only initials for contact names in the output tables.
  • [EXTERNAL_DOWNLOADS]: The skill references resources from Lusha's official website.
  • Evidence: Footer reference to https://www.lusha.com/campus/plays/customer-health-skill/.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 11:07 AM
Security Audit — agent-trust-hub — customer-health