using-vit

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to follow accounts and run "vit skim --json" to read caps (ATProto user-generated posts) from followed accounts and then use those caps (e.g., for remix/ship), so it ingests untrusted public third-party content as part of its workflow (see SKILL.md §3 "Run vit skim --json to read caps from followed accounts" and COMMANDS.md vit skim output description).