boards-work-item-summary
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources that could contain untrusted instructions.
- Ingestion points: Work item descriptions, reproduction steps, and user comments retrieved from Azure DevOps REST API calls described in
SKILL.md. - Boundary markers: The skill does not define explicit delimiters or instructions to ignore potential commands embedded within the retrieved data.
- Capability inventory: The skill uses
curlfor network requests to Azure DevOps and manages local temporary files for PowerShell compatibility. - Sanitization: The instructions suggest the agent ignore HTML tags when processing external text but do not specify robust sanitization for natural language instructions.
Audit Metadata