pipelines-build-summary
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill is designed to retrieve and display content from Azure DevOps build logs and commit messages, which are external data sources that could potentially contain adversarial instructions.
- Ingestion points: Build logs are retrieved via the
pipelines_build_logtool, and commit messages are fetched usingpipelines_buildwith theget_changesaction. - Boundary markers: The skill instructions do not explicitly require the use of delimiters or 'ignore' instructions when processing or presenting the retrieved log content or commit data to the agent.
- Capability inventory: The skill has access to several Azure DevOps tools for listing and inspecting projects, definitions, builds, and logs (
core_list_projects,pipelines_definition,pipelines_build,pipelines_build_log). - Sanitization: No explicit sanitization or filtering logic is specified for the text content originating from the pipeline logs or change descriptions before it is incorporated into the agent's context.
Audit Metadata