attachment-media-handling
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill consists of documentation and conceptual code snippets for content delivery logic in a sales context.
- [INDIRECT_PROMPT_INJECTION]: The skill describes handling prospect queries to trigger content delivery. While this introduces an input surface for indirect injection, the risk is inherent to the design of conversational agents and managed through standard LLM safety protocols.
Audit Metadata