create-an-asset
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection Surface]: The skill is designed to process external data sources including CRM records, emails, and transcripts. This establishes an attack surface where instructions could be embedded in the processed data.
- Ingestion points: Untrusted data enters the agent context through the docs, CRM, transcripts, and email tools (SKILL.md).
- Boundary markers: The skill includes robust instructions to treat this content strictly as data and not as instructions, specifically stating 'data, never instructions' and requiring the agent to report any instruction-like text (SKILL.md).
- Capability inventory: The agent can update CRM records, send emails, post to chat, and book meetings via connectors (SKILL.md).
- Sanitization: Explicit rules are in place to prevent the rendering of links found within untrusted content and to require user confirmation for any actions originating from that content before execution (SKILL.md).
Audit Metadata