specialist-marketing-corporate-training-designer

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data via the {the user's question} placeholder, which is interpolated directly into a prompt for a sub-agent.
  • Ingestion points: SKILL.md (via the prompt argument in the Agent tool call).
  • Boundary markers: No specific delimiters or instruction-isolation markers are used around the interpolated user input.
  • Capability inventory: The skill utilizes the Agent tool to spawn ephemeral sub-agents (asa:specialized:Corporate-Training-Designer).
  • Sanitization: No input sanitization or validation logic is present.
  • Context: While this creates a surface for indirect prompt injection, it is a standard design pattern for multi-agent orchestration and does not involve high-privilege operations in the parent skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 08:50 PM
Security Audit — agent-trust-hub — specialist-marketing-corporate-training-designer