aeon-deep-research

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime “deep research” workflow explicitly pulls from primary/secondary/market sources (e.g., media, audit reports, public filings, and market signal), which are outsider-authored web content ingested as readable text into the agent’s LLM context via the configured search/scraping provider.