apibible

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md shows the agent uses Membrane to fetch and run API.Bible actions (e.g., get-verse, search-bible and proxying arbitrary /path/to/endpoint) so it ingests public third-party content from API.Bible which the agent is expected to read and could materially influence subsequent outputs or actions.