wrike-automation
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines workflows for retrieving and processing task data from Wrike, which constitutes a surface for indirect prompt injection if that data contains malicious instructions.
- Ingestion points: Task titles and descriptions (noted as supporting HTML) retrieved via
WRIKE_FETCH_ALL_TASKSandWRIKE_GET_TASK_BY_ID. - Boundary markers: The instructions do not prescribe the use of delimiters or specific system instructions to ignore embedded commands within the processed task data.
- Capability inventory: The skill utilizes tools for modifying the workspace, creating/deleting folders (
WRIKE_DELETE_FOLDER), and inviting users (WRIKE_CREATE_INVITATION), which could be targeted by an injection attack. - Sanitization: There are no instructions for sanitizing or filtering HTML content from retrieved descriptions before processing.
Audit Metadata