write-pr
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a standard administrative workflow for repository maintenance and code review preparation. It does not introduce any hidden behaviors or unauthorized network activities.\n- [COMMAND_EXECUTION]: Legitimate use of
gitandgh(GitHub CLI) commands to interact with the local repository and GitHub API for PR management. The commands are scoped to the current branch and repository.\n- [INDIRECT_PROMPT_INJECTION]: The skill involves reading untrusted content from issue reports and code diffs. This creates a surface for indirect prompt injection, but the skill context limits the impact to the generation of a PR description, which is typically reviewed by a human before merging.
Audit Metadata