workflow-big-feature

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

• Third-party content exposure detected (high risk: 0.85). The required workflow includes $web-research (and $deep-research), which by definition fetches public web content at runtime; that fetched outsider-authored free text is then ingested into the agent’s LLM context during research.

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

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