continuous-learning-v2

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

• Third-party content exposure detected (high risk: 0.90). The skill's CLI explicitly fetches and ingests arbitrary HTTP/HTTPS URLs in scripts/instinct-cli.py (cmd_import uses urllib.request.urlopen to load a provided URL) and SKILL.md documents the /instinct-import flow, and those imported files are parsed into "instinct" rules that can be added/updated and later used to drive evolve/promote/agent behavior—so untrusted third‑party content can directly influence agent actions.