gh-stack

Pass

Audited by Gen Agent Trust Hub on Oct 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the gh-stack extension using gh extension install github/gh-stack. This fetches code from GitHub's official repository, which is a trusted source.
  • [COMMAND_EXECUTION]: The skill executes several shell commands to manage the environment and Git workflow, including gh auth status, git config rerere.enabled true, and various gh stack subcommands. These are standard developer operations for branch and PR management.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources through commands like gh stack view --json and gh stack checkout <pr-number-or-url>.
  • Ingestion points: Branch names, pull request titles, and pull request metadata are ingested into the agent's context during stack visualization and checkout (SKILL.md).
  • Boundary markers: None provided in the instructions to delimit external PR data from agent instructions.
  • Capability inventory: The agent can perform significant Git operations including gh stack push, gh stack rebase, and gh stack link (SKILL.md).
  • Sanitization: There is no mention of sanitizing or escaping content retrieved from GitHub PRs before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 17, 2026, 07:55 PM