apps

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly advertises "web search" among the 250+ apps and shows examples running a search app (e.g., inferencesh/tavily-search with a query), indicating the agent can fetch and ingest open/public web content that may be untrusted and could influence subsequent actions.