narrative-resonance-monitor

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

• Third-party content exposure detected (high risk: 0.85). At runtime the skill runs scripts/connectors/tavily.py --answer (and also gdelt.py/bluesky.py) which fetches/ingests public web/social text authored by outsiders, and that free-form content is then fed into the agent’s LLM context as part of the proxy-labeled AI-answer perception and resonance signals.