airbyte-sdk-reference
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides tools for reading data from external services (e.g., Jira, Slack), which could contain untrusted instructions.\n
- Ingestion points: Data is ingested through the
connector.executemethod (referenced inclaude-sdk.mdandpydantic-ai.md) when retrieving content from external APIs.\n - Boundary markers: No explicit delimiters or "ignore" instructions are shown in the tool implementation examples.\n
- Capability inventory: The skill enables the agent to interact with various third-party platforms via network requests to the Airbyte API.\n
- Sanitization: Content from external APIs is serialized to JSON and passed to the agent without specific sanitization or filtering shown in the examples.
Audit Metadata