new-issue
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (
gh) andgitto perform operational tasks such as repository verification (gh repo view), authentication checks (gh auth status), and issue creation (gh issue create). These commands are standard for the skill's stated purpose. - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect injection as it processes conversation history, including code snippets and error logs, to generate issue content.
- Ingestion points: Reads current conversation history and user-provided descriptions as defined in the
Inputsection ofSKILL.md. - Boundary markers: The skill forces a structured Markdown output and requires translation of all content into English, which acts as a basic delimiter for the generated content.
- Capability inventory: The skill has the capability to perform network-based write operations via the
gh issue createcommand. - Sanitization: Security risk is mitigated by a mandatory human-in-the-loop review step (Step 3) using a confirmation tool. This requires the user to explicitly verify the final content and target repository before the command is executed.
Audit Metadata