curate-whats-new
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- Command Execution: The skill executes shell commands using the GitHub CLI to list merged pull requests from the official documentation repository. This is a functional requirement for retrieving documentation history and represents standard developer workflow.
- Indirect Prompt Injection Surface: The skill processes external data from GitHub pull requests, including titles, descriptions, and code diffs. Because this content originates from various contributors, it represents a surface where specifically crafted text could attempt to influence the agent's behavior. The current procedure does not detail specific sanitization steps or boundary markers to isolate this external content from the core instructions, which is a common security consideration when processing data from public repositories.
Audit Metadata