mathematical-proofs-mentor

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow is to perform “targeted web searches” and “record each source” (i.e., fetch public web pages/articles) before trusting the skill, and that fetched outsider-authored free text would be ingested into the agent’s LLM context via the web research step.

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

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