newsworthiness-check
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill implements a structured evaluation logic with specific scoring anchors. It includes ethical constraints and "kill switches" to prevent the agent from generating responses for inappropriate content (e.g., tragedies). There are no instructions that attempt to override platform safety filters or extract internal configuration.
- [DATA_EXFILTRATION]: No unauthorized data access or exfiltration patterns were detected. The skill correctly identifies its reliance on external tools (news-search, X API) for real-time data, which is standard for its intended use case.
- [REMOTE_CODE_EXECUTION]: No remote code execution or package installation commands are present. The skill relies entirely on natural language instructions and handoffs to other skills.
- [COMMAND_EXECUTION]: There is no evidence of shell command execution or use of dynamic context injection syntax.
Audit Metadata