SharePoint Automation
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill accesses and processes external data from SharePoint environments, which may contain malicious instructions for the agent.
- Ingestion points: Tools like SHARE_POINT_SEARCH_QUERY, ONE_DRIVE_GET_SHAREPOINT_LIST_ITEMS, and SHARE_POINT_GET_SITE_PAGE_CONTENT in SKILL.md ingest untrusted content from the environment.
- Boundary markers: The skill does not provide instructions for using delimiters or boundary warnings to protect against instructions embedded in retrieved data.
- Capability inventory: The skill includes write capabilities such as creating lists and folders via SHARE_POINT_SHAREPOINT_CREATE_LIST and SHARE_POINT_SHAREPOINT_CREATE_FOLDER in SKILL.md.
- Sanitization: There is no evidence of sanitization or filtering of external data before it is interpreted by the agent.
Audit Metadata