project-intelligence-change-event-extraction
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, data exfiltration, or credential exposure risks were identified. The skill's primary function is to read project documents and update a SharePoint list, which is consistent with its stated purpose.
- [SAFE]: The skill uses established SharePoint data structures and follows a structured workflow for information extraction and reporting. All data interactions are confined to the user's SharePoint site.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes untrusted documents from a SharePoint library.
- Ingestion points: Reads every document in the 'Project Documents' library and its associated metadata (SKILL.md).
- Boundary markers: No explicit instructions are given to the agent to treat document content as data and ignore embedded instructions.
- Capability inventory: The skill has the capability to write entries into a 'Change Events' SharePoint list and generate multi-level summaries in the chat interface.
- Sanitization: No specific validation or sanitization routines are mentioned for the data extracted from documents before it is recorded in the list.
Audit Metadata