elysiajs

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs the agent to "Always consult https://elysiajs.com/llms.txt" for code examples and the latest API, which requires fetching and interpreting content from a public third-party site that can materially change code-generation/behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs "Always consult https://elysiajs.com/llms.txt" at runtime, which means the agent would fetch external content that can change prompts/instructions and thereby directly control the agent's behavior (https://elysiajs.com/llms.txt).