sumsub-analyze-regulation

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

• Third-party content exposure detected (high risk: 0.70). The required workflow ingests the regulation document’s text (Step 2 “Extract from the document” / Step 3 “My Understanding”); if that document is outsider-authored (e.g., downloaded from the public web or provided by someone else), its free-form body text can be read and then fed into the agent’s LLM context for analysis.

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

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