expose-agentkit-mcp
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary use case involves fetching data from external, untrusted sources (Gmail) and using that data to perform actions (creating Google Calendar events) through an LLM agent.
- Ingestion points: The skill uses the
gmail_fetch_mailstool to ingest external email content into the agent's context (SKILL.md). - Boundary markers: The provided implementation samples do not include specific boundary markers or instructions to the agent to ignore instructions embedded within the fetched emails.
- Capability inventory: The skill possesses capabilities to execute tools like
googlecalendar_create_eventand arbitrary tool execution via a ReAct agent (SKILL.md). - Sanitization: The code samples do not demonstrate sanitization or filtering of the fetched email content before it is processed by the LLM.
Audit Metadata