045-planning-azure-devops
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a robust defense against indirect prompt injection by explicitly instructing the agent to refuse the ingestion or analysis of descriptive Azure DevOps fields (titles, descriptions, comments, and discussion text).
- [SAFE]: The skill mandates an interactive verification process for tool installation. If the Azure CLI or the azure-devops extension is missing, the agent is instructed to stop and ask for user consent before providing installation guidance.
- [SAFE]: Hardcoded credentials, tokens, and Personal Access Tokens (PATs) are strictly forbidden. The instructions explicitly prohibit printing or requesting sensitive authentication material in the chat.
- [SAFE]: The skill limits its operational scope to work item IDs, counts, and derived links, minimizing the risk of accidental data exposure from the Azure DevOps platform.
Audit Metadata