sales-call-prep-assistant

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it instructs the agent to research and process external data, which could contain malicious instructions.
  • Ingestion points: Company news, stakeholder backgrounds, and other prospect-related research data processed in SKILL.md via the agent's research capabilities.
  • Boundary markers: No specific delimiters or instructions are provided to help the agent distinguish between its core instructions and data retrieved from external sources.
  • Capability inventory: The skill uses the agent's general knowledge and default search/research capabilities to generate briefs and suggested questions.
  • Sanitization: There are no instructions for sanitizing, escaping, or filtering content retrieved from the web or other external prospect research sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 07:25 AM
Security Audit — agent-trust-hub — sales-call-prep-assistant