image-generation

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly directs the agent to "run focused research" (SKILL.md workflow step 2) and the JSON prompt pipeline includes source_inputs and research_anchors (which accept URLs) and records public reference URLs (references/* and source_map), meaning the agent is expected to ingest and act on open/public third‑party web content as part of prompt creation and generation decisions.