skills/dotnet/maui/issue-triage/Gen Agent Trust Hub

issue-triage

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [Command Execution]: The skill executes PowerShell scripts and uses the GitHub CLI (gh) to perform repository operations. These commands are used to query issue data and apply triage decisions (milestones and labels) to the dotnet/maui repository. Evidence includes calls to gh issue edit and gh api within the provided scripts.
  • [External API Interaction]: The scripts interact with the official GitHub API (api.github.com) and GraphQL endpoints to retrieve milestone, label, and issue information. This communication is essential for the skill's functionality and targets well-known service infrastructure.
  • [Indirect Prompt Injection Surface]: The skill ingests untrusted data from GitHub (issue titles and comments) and presents them to the agent.
  • Ingestion points: scripts/query-issues.ps1 retrieves title and comment data.
  • Boundary markers: The triage presentation template in SKILL.md does not use explicit delimiters to isolate external content.
  • Capability inventory: The skill has the capability to modify repository state via gh issue edit and gh pr edit commands.
  • Sanitization: The scripts perform basic whitespace cleaning for display purposes but do not implement strict content sanitization. This is a standard consideration for tools processing external feedback.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 02:35 AM