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

gh-stack

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONPRIVILEGE_ESCALATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill suggests installing the 'github/gh-stack' extension for the GitHub CLI. This is an official extension from a well-known service provider.
  • [REMOTE_CODE_EXECUTION]: The skill executes commands from the installed GitHub extension to perform stack management operations.
  • [COMMAND_EXECUTION]: Utilizes standard Git and GitHub CLI commands to interact with the repository and manage pull requests.
  • [INDIRECT_PROMPT_INJECTION]: The skill handles branch names and pull request metadata derived from the repository and API. While this allows for processing external data, the workflow is confined to standard development operations with low inherent risk.
  • Ingestion points: Branch names and PR metadata from local git and GitHub API.
  • Boundary markers: Not explicitly defined.
  • Capability inventory: Branch creation, committing, pushing, and PR merging.
  • Sanitization: Dependent on CLI tool validation.
  • [PRIVILEGE_ESCALATION]: The skill modifies local Git settings but instructions require the agent to seek explicit user approval first.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 08:45 PM
Security Audit — agent-trust-hub — gh-stack