segment-audience

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions are aligned with the stated objective of audience management.
  • [SAFE]: The skill accesses local configuration files and processes PII (names, emails) as part of its core functionality for CRM data management.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes data from external APIs and local configuration files. 1. Ingestion points: profile.json, _manifest.json, and external CRM/Email API data. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the logic. 3. Capability inventory: Operations are restricted to MCP-mediated API calls and local logging; no shell or dynamic code execution capabilities were found. 4. Sanitization: No explicit data validation or escaping steps are defined. The risk is assessed as safe given the tool's limited capability scope and intended use case.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 12:41 AM
Security Audit — agent-trust-hub — segment-audience