devops-requirements

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the dxs command-line tool to retrieve work items and inspect report files. These commands are integral to the skill's utility and are associated with the vendor's toolset.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the download of attachments from Azure DevOps, such as specification documents and sample reports, which are then stored in a local directory for further processing.
  • [PROMPT_INJECTION]: The skill ingests data from Azure DevOps work items, which presents an indirect prompt injection surface where instructions could be embedded in work item fields or attachments.
  • Ingestion points: External data from Azure DevOps work item fields (description, design) and file attachments (SKILL.md).
  • Boundary markers: No explicit markers are used to separate untrusted external content from the agent's core instructions.
  • Capability inventory: Ability to execute dxs CLI commands and write files to the local artifact directory (SKILL.md).
  • Sanitization: The instructions do not specify any validation or filtering of the content retrieved from the external source.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 03:43 PM