twenty-record-presentation

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to retrieve and display data from the Twenty CRM, creating a surface for indirect prompt injection.\n- Ingestion points: CRM record data is ingested via MCP tools such as execute_tool as specified in the SKILL.md file.\n- Boundary markers: The instructions do not define clear delimiters or include 'ignore embedded instructions' warnings for the data being processed from the CRM.\n- Capability inventory: The skill focus is restricted to data presentation (formatting tables, blocks, and links) and does not include scripts with capabilities for subprocess execution, file system modification, or direct network operations.\n- Sanitization: No explicit sanitization or validation logic is provided for the content of the CRM records before they are interpolated into the display output; the skill explicitly instructs the agent to keep record values unchanged.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 08:29 PM
Security Audit — agent-trust-hub — twenty-record-presentation