venice-augment

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md describes runtime ingestion of outsider-authored content via Venice’s POST /augment/scrape (fetches a caller-supplied url and returns scraped content markdown) and POST /augment/search (returns search results[*].content from third-party pages), which the agent can then pass to an LLM.