image-similarity-finder

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

• Third-party content exposure detected (high risk: 0.75). Outsider free text can enter the LLM context via the runtime API response from the proxy endpoint /api/v1/tools/linkfox/amazon/searchByImage, which returns outsider-authored Amazon product fields (e.g., product titles/brands) that are then embedded into the generated markdown/JSON output and thus into the agent’s LLM context.