sharepoint-api
Warn
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The
scripts/session-manager.shscript contains aforce_cleanupfunction that executespkill -9 Chrome, which terminates all Google Chrome processes on the host system regardless of their association with this skill. It also recursively deletes allSingletonLockfiles within the~/agent-browser-profilesdirectory. - [DYNAMIC_EXECUTION]: Operational scripts such as
list-files.sh,download-file.sh, andupload-file.shuseagent-browser evalto execute dynamically generated JavaScript code blocks within a browser session to perform authenticated SharePoint actions. - [INDIRECT_PROMPT_INJECTION]: The skill processes file metadata from SharePoint and allows user-provided input to influence API queries.
- Ingestion points: File metadata and folder paths retrieved via
RenderListDataAsStreaminscripts/list-files.shandscripts/upload-file.sh. - Boundary markers: No explicit delimiters or boundary instructions are used when passing external data to subsequent agent actions.
- Capability inventory: The skill possesses capabilities for reading/writing files, performing network operations, and capturing network traffic via HAR capture.
- Sanitization: The
build_viewxmlfunction inscripts/list-files.shdirectly interpolates user-provided shell variables (e.g.,$FILE_TYPE,$MODIFIED_AFTER) into a CAML XML query string without validation or escaping, which can lead to query injection in the SharePoint API.
Audit Metadata