zensical-site

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md workflow explicitly instructs the agent to "Collect source material from zensical.org" and the references/docs-reference-outline.md lists many https://zensical.org/... pages the agent is expected to load and act on, so the agent will fetch and interpret public third-party site content that can influence its outputs.