evolve

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

• Third-party content exposure detected (high risk: 0.70). The skill's CLI and documentation explicitly accept and process arbitrary external assets (e.g., "python3 $ENGINE recraft vectorize IMAGE_URL" in engine.py and the Asset Batch / asset-generation rules in SKILL.md that ingest user-provided logo references or remote images), so the agent can fetch and read untrusted public URLs and then use that content to drive generation/modification decisions.