finishing-a-development-branch

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes various development commands including test runners such as npm test, cargo test, pytest, and go test, as well as git commands like git merge, git push, and git worktree. These are standard operations for a development-focused skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data such as branch names and pull request content which is then used in shell commands and tool calls.
  • Ingestion points: External data enters through branch names and user-provided pull request titles/summaries as described in SKILL.md.
  • Boundary markers: The skill uses a quoted heredoc ('EOF') in the PR creation command, which provides a shell-level boundary but does not prevent the agent from being influenced by instructions embedded within the text content.
  • Capability inventory: The skill has the capability to execute shell commands via git, the GitHub CLI, and various language-specific test runners.
  • Sanitization: There is no explicit sanitization or validation of the branch names or PR metadata before they are interpolated into commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 12:55 PM