find-reviewable-pr
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [Command Execution]: The skill executes a PowerShell script that uses the GitHub CLI (
gh) to query repository data. This includes usingInvoke-Expressionto handle command execution and retries for API calls. - [External Data Processing]: The script retrieves and processes metadata from pull requests, such as titles and labels, from the
dotnet/mauianddotnet/docs-mauirepositories. - [Indirect Prompt Injection Consideration]: The skill ingests untrusted data from pull request metadata in the
query-reviewable-prs.ps1script. While the agent uses structured markdown tables as boundaries for the output, no explicit sanitization is performed on the ingested titles. The skill's capabilities are focused on data retrieval and presentation. - [Secure Input Handling]: Script parameters are strictly defined with
ValidateSetand specific types, which limits the potential for unexpected input processing.
Audit Metadata