press-release-writer
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional text and formatting guidelines for generating press releases. It does not include any code, external library requirements, or network operations.- [PROMPT_INJECTION]: The skill utilizes a template structure with placeholders like
{主体}and{事件}for data ingestion. While it lacks explicit boundary markers to isolate these inputs from the system prompt, the skill does not expose any dangerous tools or system capabilities (such as file writing, network access, or command execution) that could be leveraged by an indirect prompt injection attack.
Audit Metadata