i-ching-oracle-guide

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). The required workflow is a manual “fresh web research” step (targeted web searches) before trusting the skill, and that runtime web-fetched free text from outsider-authored pages would be ingested into the agent’s LLM context via the research/distillation steps.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)