name-project

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 perform web searches and use external tools (name generators, word-relationship APIs) and to check npm, GitHub, and domains as part of its "Research Step" and collision checks, which ingests untrusted public content that can materially influence name selection and subsequent actions.