agent-platforms

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to "use WebFetch" to retrieve a public GitHub raw URL (https://raw.githubusercontent.com/gmh5225/awesome-skills/refs/heads/main/README.md), which is user-generated third-party content the agent would read and that could influence subsequent actions.