sdlc-create-pull-request
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute
azCLI commands (specificallyaz reposandaz rest) to interact with Azure DevOps repositories. It also references a companion PowerShell scriptscripts/New-AdoWorktreePullRequests.ps1as a logic reference for branch discovery and PR creation. - [INDIRECT_PROMPT_INJECTION]: The skill generates PR titles and descriptions by processing data from potentially untrusted sources.
- Ingestion points: The agent reads content from
sdlc/<work-item>/pr-summary.md,intent.md,spec.md,plan.md, as well as branch diffs and commit messages from the repository. - Boundary markers: The workflow includes a mandatory "Preview and confirm" step (Step 5) where the user must review the generated content before any PR is created, serving as a human-in-the-loop security boundary.
- Capability inventory: The skill possesses the capability to perform network operations (
az repos pr createto Azure DevOps) and file system writes (updatingpr-summary.mdandplan.md). - Sanitization: No explicit sanitization or escaping mechanisms for the ingested text are described in the instructions before the data is used to generate the PR narrative.
Audit Metadata