asana
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the Asana OpenAPI specification from the official Asana GitHub repository for reference documentation.\n- [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to ingest and process data from Asana (e.g., task descriptions, comments), which constitutes a vulnerability surface for indirect prompt injection.\n
- Ingestion points: Operations such as references/operations/getTask.md and references/operations/getStoriesForTask.md allow the agent to read potentially untrusted content.\n
- Boundary markers: The reference files do not specify boundary markers or instructions to isolate untrusted data.\n
- Capability inventory: The skill grants the agent capabilities to modify Asana data via various POST, PUT, and DELETE operations (e.g., references/operations/createTask.md), which could be leveraged following a successful injection.\n
- Sanitization: No sanitization or validation procedures for API-sourced data are described in the documentation.
Audit Metadata