nondominium-holochain-dna-dev

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 instructs the agent to fetch and interpret entries from other agents (e.g., the "Data Access Patterns" use get_links(...) and get(...), and "Remote Agent Calls" use call_remote(...)), which are untrusted, user-generated Holochain/DHT content that the agent reads and uses to drive decisions and actions.