life-capture

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). This skill requires writing the user's raw text verbatim into an output file ("Body = raw user text only"), which forces the agent to include any secrets present in the user's input verbatim and therefore poses an exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.30). In SKILL.md the required runtime workflow ingests outsider-authored free text from the user (“Body = raw user text only”) and writes it into layout.inbox_dir as an unprocessed inbox note.