china-content-research

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No security issues detected. The skill consists entirely of instructional guidelines for market research and content synthesis.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to ingest and process untrusted data from external WeChat articles. This is a low-risk surface inherent to research functions.
  • Ingestion points: Extracted content from WeChat Official Accounts (SKILL.md, Step 2).
  • Boundary markers: Absent.
  • Capability inventory: Information extraction and synthesis; no subprocess calls, file-writes, or dangerous network operations are present.
  • Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 07:32 PM
Security Audit — agent-trust-hub — china-content-research