skills/bastani-inc/atomic/gh-stack/Gen Agent Trust Hub

gh-stack

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches and installs the gh-stack extension from the official GitHub organization repository. This is a neutral operation as the source is a trusted organization.
  • [COMMAND_EXECUTION]: Uses standard version control tools and follows non-interactive best practices for agents, including mandatory use of flags like --auto and --json to prevent interactive hangs.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes JSON output from the GitHub CLI. Ingestion point: JSON data from gh stack view. Boundary markers: None. Capability inventory: Shell command execution and file system access. Sanitization: None. While a surface exists, the instructions specify structured data parsing which is a standard and secure way to handle tool output.
  • [METADATA_POISONING]: The metadata lists the author as 'github' while the registration is under 'bastani-inc'; however, the content accurately describes the official tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 07:57 AM
Security Audit — agent-trust-hub — gh-stack