skills/kjanat/skills/gh-stack/Gen Agent Trust Hub

gh-stack

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the github/gh-stack extension via the GitHub CLI. This is an official extension provided by the GitHub platform to manage stacked pull requests.
  • [COMMAND_EXECUTION]: The skill uses various git and gh CLI commands, such as gh stack submit and gh stack rebase, to automate the management of pull request layers and repository ancestry. These commands are executed within the user's local repository environment to perform authorized repository operations.
  • [PROMPT_INJECTION]: The skill is designed to process repository data which may contain untrusted content from commit messages or branch names.
  • Ingestion points: Data enters the agent's context through commands like git log and gh stack view --json as described in SKILL.md and references/commands.md.
  • Boundary markers: The instructions do not include specific delimiters or instructions for the agent to disregard instructions embedded within commit messages or PR bodies.
  • Capability inventory: The skill is capable of modifying the repository and pull request state using gh stack submit and gh stack merge operations.
  • Sanitization: While status information is retrieved in structured JSON format, the skill uses commit messages to generate pull request metadata without specific sanitization steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 11:28 AM
Security Audit — agent-trust-hub — gh-stack