coder-ado

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized privilege escalations were detected. The skill instructions focus on valid software development lifecycle tasks.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes data from external work items.
  • Ingestion points: Work item details, comments, and link metadata retrieved from the Azure DevOps MCP server.
  • Boundary markers: Absent. The skill does not instruct the agent to use delimiters or ignore instructions embedded within the work items.
  • Capability inventory: The skill can modify source code, perform Git operations (branch, commit, push), and update external work item statuses.
  • Sanitization: No sanitization or filtering logic for work item content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 06:26 PM