query-integration-data
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data fetched from external integrations (Slack messages, GitHub issues, HubSpot contacts, etc.) and data warehouses. This data is considered untrusted and could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Data retrieved via API clients (e.g.,
@linear/sdk) and SQL queries viaexecuteSql. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the provided implementation examples.
- Capability inventory: The skill utilizes the
code_executionsandbox which has the ability to read/write files in.agents/outputs/, perform network operations via APIs, and launch additionalSMALL_TASKsubagents. - Sanitization: The skill does not specify any sanitization or validation logic for the data retrieved from external sources before it is used in further logic or returned to the user.
Audit Metadata