github
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill uses the official
ghCLI to interact with GitHub repositories, which is its primary intended purpose. - [EXTERNAL_DOWNLOADS] (SAFE): The metadata specifies the installation of the
ghbinary through trusted system package managers like Homebrew and APT. - [PROMPT_INJECTION] (LOW): The skill has an attack surface for indirect prompt injection as it processes untrusted data (like PR descriptions or issue comments) from external GitHub repositories. Evidence Chain: 1. Ingestion points: Data enters via
gh pr,gh issue, andgh apicommands. 2. Boundary markers: Absent; there are no instructions to the agent to treat external content as untrusted. 3. Capability inventory: The skill allows the agent to read and potentially modify GitHub data through theghCLI. 4. Sanitization: Absent; the content is passed directly to the agent without escaping or filtering.
Audit Metadata