gh-get-issue
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
gh(GitHub CLI) to view issue details. This is a standard and expected tool for interacting with GitHub repositories. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection attacks. It retrieves the
bodyandcommentsof a GitHub issue, which are attacker-controlled inputs, and renders them directly into the agent's context. - Ingestion points: The
gh issue viewcommand fetches untrusted data from GitHub issue descriptions and user comments (SKILL.md). - Boundary markers: Absent. The template renders the external content without using clear delimiters (such as XML tags) or instructions to ignore embedded commands.
- Capability inventory: The skill facilitates command execution via the
ghCLI and potentially other tools available in the agent's environment. - Sanitization: Absent. There is no evidence of filtering, escaping, or validation of the fetched text before it is presented to the agent.
Audit Metadata