skills/dotnet/core/release-notes/Gen Agent Trust Hub

release-notes

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • Command Execution: The skill utilizes command-line tools such as git, jq, and dnx. These are employed for routine tasks like querying repository metadata and processing structured change manifests. These operations are conducted within the context of the .NET development workflow.
  • External Package Execution: Verification steps involve running dotnet-inspect through dnx from official Microsoft Azure DevOps public feeds. This process is intended to ensure documentation accuracy by checking against the actual build artifacts. The use of official, vendor-managed NuGet sources follows established security practices.
  • Indirect Prompt Injection Surface: The skill processes external data in the form of Pull Request titles and descriptions from changes.json. Evidence of ingestion appears in references/api-verification.md and references/quality-bar.md. The agent's capabilities include executing shell commands for verification and metadata extraction. The skill manages this surface by mandating an API verification workflow and a quality bar that requires grounding all claims in official build data.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 02:31 AM
Security Audit — agent-trust-hub — release-notes