awaken

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

• Third-party content exposure detected (high risk: 0.90). The skill's Full Soul Sync and reawaken workflows explicitly fetch and read public GitHub content (e.g., the /learn https://github.com/Soul-Brews-Studio/... steps and gh issue view ... --comments commands in Phase 4) and then use those discoveries to generate the Oracle's philosophy and files, meaning untrusted third-party content is ingested and can materially influence the agent's actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The Full Soul Sync and related flows explicitly run /learn on https://github.com/Soul-Brews-Studio/opensource-nat-brain-oracle and https://github.com/Soul-Brews-Studio/oracle-v2 and use gh to read/post to Soul-Brews-Studio/arra-oracle-v3 at runtime, and the fetched repository content is used to generate the Oracle's philosophy/CLAUDE.md (directly controlling prompts/behavior), so these external GitHub repos are runtime dependencies that control agent instructions.