social-opinion-writer

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows a structured and secure workflow for document generation, focusing on official policy research and multi-stage drafting.
  • [DATA_EXFILTRATION]: While the skill uses internet access to fetch data, it targets well-known official government and political domains (e.g., gov.cn, cppcc.gov.cn, nhc.gov.cn) for public policy information. There is no evidence of unauthorized data transfer or access to sensitive local files.
  • [PROMPT_INJECTION]: The skill processes external data from web searches and user notes, which is a potential surface for indirect prompt injection. However, the skill explicitly mandates cross-referencing with official glossaries and policy maps, and includes a multi-round review process to ensure content integrity.
  • [COMMAND_EXECUTION]: The skill's file-writing activity is restricted to creating a structured workspace for the user's project (social-opinions/), which is a benign and expected behavior for a document generation agent. No dangerous shell commands are used.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 01:08 PM