six-thinking-hats

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface in its 'Writing Review' mode, where it analyzes user-provided schemes or text. Adversarial instructions hidden in these documents could attempt to influence the agent's behavior during analysis.\n
  • Ingestion points: User-provided schemes and documents processed in the 'Writing Review' mode (SKILL.md).\n
  • Boundary markers: Absent; there are no specified delimiters or instructions for the AI to ignore commands embedded in user-supplied data.\n
  • Capability inventory: Text analysis and report generation, with optional tool calls for search via baidu-search and baidu-baike.\n
  • Sanitization: No sanitization or validation of external content is described in the skill's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 03:07 AM
Security Audit — agent-trust-hub — six-thinking-hats