inspect-content-provenance

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow ingests outsider-provided free text when the user invokes the tool with python3 scripts/inspect_file.py --text 'text to inspect' and the runtime reads/analyses that text (including covert-channel scanning) via inspect_text() → core.scan_covert_channels(text) → find_c2pa_text_wrapper(text).