continuous-learning-v2

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

• Third-party content exposure detected (low risk: 0.10). The instinct import feature fetches and parses external YAML/instinct files from arbitrary URLs or local paths supplied by the user (instinct-cli.py import via urllib.request.urlopen).

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The CLI script includes an active urllib.request.urlopen function call that fetches and ingests external code or data from user-supplied URLs during the import runtime flow, presenting a weak, dynamic provenance path.