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_log tool, and commit messages are fetched using pipelines_build with the get_changes action.
  • 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
Risk Level
SAFE
Analyzed
Sep 16, 2026, 10:56 AM
Security Audit — agent-trust-hub — pipelines-build-summary