opennews
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains a section titled '内容合规要求' (Content Compliance Requirements) that instructs the agent to apply 'extremely conservative' filters to API results. It provides a list of specific political and legal criteria for suppressing content and mandates a hardcoded refusal message ('返回结果有风险，不适合展示') if those criteria are met. This overrides the agent's standard safety guidelines with external, author-defined censorship rules.
Audit Metadata