log-onboarding-issues
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- COMMAND_EXECUTION (LOW): The skill constructs and executes shell commands using the GitHub CLI (gh) to manage issues. This follows a standard template and is consistent with the skill's primary purpose.
- PROMPT_INJECTION (LOW): The skill presents an attack surface for Indirect Prompt Injection (Category 8) because it takes findings from one skill (/check-onboarding) and uses them to construct parameters for GitHub commands. Evidence: 1. Ingestion points: Audit findings returned by the /check-onboarding skill are used in the step to create issues. 2. Boundary markers: Absent; findings are directly interpolated into the --title and --body fields of the 'gh issue create' command without delimiters. 3. Capability inventory: Performs network-based write operations to GitHub via the 'gh' tool. 4. Sanitization: No explicit validation or escaping is performed on the findings before they are passed to the shell environment.
Audit Metadata