laniameda-gallery-ingest

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly supports ingesting remote, arbitrary URLs (see "Supported content → Remote URL ingestion" in SKILL.md and the remote URL example in references/ingest-examples.md) and the runtime script (scripts/ingest.ts) forwards a provided url/imageUrl to the backend ingest action, so untrusted third-party content can be ingested and interpreted as prompts/assets and therefore could influence subsequent actions.