skills/microsoft/aspire/azdo-internal/Gen Agent Trust Hub

azdo-internal

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection Surface: The skill instructs the agent to retrieve and analyze build logs and timeline data from Azure DevOps. This represents an indirect prompt injection surface where data generated during the build process (which may include output from external pull request code) could influence the agent's logic.
  • Ingestion Points: Build timeline data and logs are fetched using commands like az devops invoke --area build --resource Timeline.
  • Boundary Markers: The instructions do not currently specify delimiters or specific warnings for the agent to disregard instructions embedded within these logs.
  • Capability Inventory: The skill involves capabilities such as triggering new builds (az pipelines run) and pushing code to internal mirrors (git push).
  • Sanitization: There are no explicit instructions for sanitizing or filtering the log content before processing.
  • Vendor-Specific Infrastructure Access: The skill identifies and interacts with resources hosted on dev.azure.com/dnceng, which is an internal Microsoft organization. These interactions are consistent with the skill's stated purpose and the author's identity.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 09:48 PM