task-observer
Warn
Audited by Snyk on Aug 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In the task-observer runtime, it ingests user-facing free text from the ongoing conversation (including review/post-task feedback) and logs it into
skill-observations/log.md, meaning outsider-authored text can directly influence what the model reads and records.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata