sharepoint-list-formatter
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [Untrusted Data Ingestion]: The skill is designed to process content from SharePoint lists, which are external sources of data. This creates a surface for indirect prompt injection, where instructions embedded within list items (such as the Title or Description fields) could potentially influence the agent's behavior. The skill would benefit from boundary markers or explicit instructions to ignore any commands found within the formatted data.
- [Dynamic Link Construction]: The instructions direct the agent to build 'Open' links by concatenating a tenant domain with values like 'site name', 'list name', and 'itemID' retrieved from the source data. While this facilitates navigation, the integrity of these links depends on the reliability of the source data to ensure they point to the correct SharePoint resources.
- [Markdown Injection Considerations]: The skill does not specify sanitization for the data fields included in the table. If a SharePoint item contains Markdown control characters (e.g., brackets or pipes) in its Title or Description, it could unintentionally break the table formatting or manipulate the destination of the 'Open' links presented to the user.
Audit Metadata