openclaw-executive-assistant-workflows

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 files—e.g., exported .eml email bodies placed in 03-offline-communications-triage/eml/ (and similarly “unknown files” in 01-data-intake-review/incoming/)—which the agent reads and includes in the LLM context for triage/reporting.

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

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