lyra

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly says the --research flag triggers WebSearch and instructs the agent to incorporate web findings into prompt optimization (e.g., "Use WebSearch" in the --research Flag Behavior), which means it fetches and ingests untrusted public web content that can influence subsequent actions and prompts.