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-stackextension usinggh 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 variousgh stacksubcommands. 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 --jsonandgh 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, andgh stack link(SKILL.md). - Sanitization: There is no mention of sanitizing or escaping content retrieved from GitHub PRs before processing.
Audit Metadata