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