release-notes-generator
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to influence the agent's output.
- Ingestion points: Untrusted content is ingested from Azure DevOps work item descriptions (
dxs source workitems --description), commit messages (dxs source compare), and source code diffs (dxs source diff) across potentially hundreds of dependencies. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when interpolating this external content into the agent's prompt for summarization.
- Capability inventory: The agent has the capability to read extensive repository data and work item history. While it primarily writes text output, the processed content directly shapes the 'Customer Release Notes' and 'Technical Release Notes'.
- Sanitization: No sanitization or filtering of the ingested natural language descriptions or code comments is mentioned in the workflow.
Audit Metadata