implement-next
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data by reading GitHub issue bodies and comments via
gh issue view --commentsandgh api. This data is then used to guide the implementation of the ticket. There are no explicit boundary markers or sanitization steps mentioned for this external content, creating a surface where malicious instructions in a ticket could influence the agent's behavior during the implementation phase. - [COMMAND_EXECUTION]: The skill instructs the agent to execute specific shell commands using the GitHub CLI (
gh) and Git. This includes modifying issue assignments (gh issue edit), querying the GitHub API (gh api), and managing local repositories (git worktree add). While these commands are standard for the skill's purpose, they represent the capability tier available to the agent when processing potentially malicious ticket data.
Audit Metadata