openclaw-executive-assistant-workshop

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow ingests outsider-authored free text from user-provided input files—e.g., exported .eml email bodies placed in code-along/03-offline-communications-triage/eml/ (or other “incoming/” files) are read as context and fed into the LLM for triage/intake, and those emails/files are authored by parties other than the operating user.