The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from Wrike, such as task descriptions and titles, which are potentially controlled by other users. This creates a surface for indirect prompt injection if that data contains malicious instructions intended to manipulate the agent.
Ingestion points: SKILL.md defines workflows using WRIKE_FETCH_ALL_TASKS, WRIKE_GET_TASK_BY_ID, WRIKE_GET_FOLDERS, and WRIKE_GET_CONTACTS to pull data into the agent context.
Boundary markers: The instructions do not define specific delimiters or instructions to treat data from Wrike as untrusted content.
Capability inventory: The skill has significant capabilities including creating tasks (WRIKE_CREATE_TASK), deleting folders (WRIKE_DELETE_FOLDER), deleting spaces (WRIKE_DELETE_SPACE), and inviting new users (WRIKE_CREATE_INVITATION).
Sanitization: There is no evidence of content sanitization or validation for data retrieved from the Wrike API.

wrike-automation