git-remote-pr
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONPRIVILEGE_ESCALATION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
gitand GitHub CLI (gh) tools to perform repository state collection and pull request management operations. - Evidence: Found in
scripts/prepare-pr.ps1andscripts/execute-pr.ps1scripts. - [DYNAMIC_EXECUTION]: The integration test harness dynamically generates and executes PowerShell code via the
-EncodedCommandparameter to facilitate failure injection and mocking. - Evidence:
scripts/test-pr.ps1contains a Base64-encoded script block passed to a new PowerShell process. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content, such as commit messages and code diffs, to generate pull request descriptions.
- Ingestion points:
scripts/prepare-pr.ps1collects data fromgit logandgit diffoutputs. - Boundary markers: The skill implements strict structural enforcement in
scripts/pr-common.ps1(Assert-PrBodyStructure) to ensure the agent's generated description conforms to a safe schema. - Capability inventory: The skill's write capabilities are scoped to
git pushandgh prmetadata updates. - Sanitization: It actively filters non-portable content like
diffhunk://links and maps file changes to reviewer-oriented themes. - [PRIVILEGE_ESCALATION]: The test suite adjusts file execution permissions to create a mock environment for the GitHub CLI.
- Evidence:
scripts/test-pr.ps1executeschmod +xon a dynamically created shim script in a temporary directory.
Audit Metadata