axiom-network-framework-ref

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly shows runtime discovery and ingestion of untrusted endpoints (e.g., NetworkBrowser / Wi‑Fi Aware examples in "4.7 NetworkBrowser & Wi‑Fi Aware" and the NWBrowser/bonjour examples) that the agent connects to and decodes (via TLV/Coder/receive), meaning arbitrary third‑party/local device content is read and can drive behavior.