agent-e2e

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

• Third-party content exposure detected (high risk: 1.00). The skill's workflows and examples (e.g., SKILL.md and examples/*.yaml such as examples/github-login-error.yaml and github-pr-review.yaml) explicitly direct the agent to open and snapshot public websites like https://github.com, extract dynamic content (PR numbers, order IDs), and use those values to drive subsequent actions, meaning the agent will fetch and interpret untrusted, user-generated third‑party web content as part of its execution.