rfp-response-content-finder
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions define a legitimate business workflow for document retrieval and summarization within a managed SharePoint environment.
- [PROMPT_INJECTION]: Analysis of the attack surface for indirect prompt injection: (1) Ingestion points: The skill processes data from the 'RFP Tracker' list and multiple SharePoint document libraries as described in Steps 1 and 3. (2) Boundary markers: The skill does not explicitly specify delimiters or ignore-instructions for text extracted from retrieved documents. (3) Capability inventory: The skill utilizes read access to SharePoint libraries and write access to update columns in the 'RFP Tracker' SharePoint list. (4) Sanitization: Content is summarized for human review in Step 5, providing a manual checkpoint, though no automated sanitization is described.
Audit Metadata