workbench-flue-agent-harness

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md "Required Source Reads" explicitly requires fetching and reading public web resources (https://flueframework.com/start.md and https://raw.githubusercontent.com/withastro/flue/refs/heads/main/README.md and models.json) as part of the agent's workflow, and those external, untrusted documents can materially affect model selection and scaffolding decisions.