continuous-learning-v2

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

• Third-party content exposure detected (high risk: 0.80). The skill's import command (scripts/instinct-cli.py :: cmd_import) explicitly fetches HTTP/HTTPS URLs via urllib.request.urlopen and parses that remote content into instinct files (and SKILL.md documents the /instinct-import workflow), so arbitrary public web pages can be ingested and turned into instincts that influence behavior.