045-planning-azure-devops

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: No attempts to override system prompts or safety filters were detected. The instructions follow standard task-oriented patterns.- [DATA_EXFILTRATION]: No unauthorized data transmission or sensitive file access was found. The skill explicitly instructs against printing Personal Access Tokens (PATs) or secrets in the chat.- [COMMAND_EXECUTION]: The skill uses standard Azure CLI (az) commands and Homebrew (brew) for environment setup. These are well-known developer tools and the skill includes an interactive confirmation step before providing installation guidance.- [SAFE]: The skill proactively mitigates indirect prompt injection by restricting output to work item IDs and counts, refusing to ingest or analyze descriptive work-item fields which could contain untrusted data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 02:07 PM
Security Audit — agent-trust-hub — 045-planning-azure-devops