finishing-a-development-branch
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard development tools including
gitand thegh(GitHub CLI) to manage branch operations, merges, and pull request creation. These commands are integral to the skill's primary purpose and are protected by mandatory hard-gates requiring user confirmation before execution of any destructive or history-altering actions. - [INDIRECT_PROMPT_INJECTION]: The skill has a potential attack surface through the processing of repository metadata. 1. Ingestion points: Branch names and commit history used for PR title and body generation (Phase 4). 2. Boundary markers: The instructions do not define specific delimiters for separating commit content from PR instructions. 3. Capability inventory: Pull request management through
gh pr createand branch operations throughgit merge. 4. Sanitization: No explicit sanitization or filtering of commit messages is described prior to interpolation into the GitHub CLI commands.
Audit Metadata