continuous-learning
Warn
Audited by Snyk on Aug 6, 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). SKILL.md describes a capture/route loop that ingests “lesson” content from chat and then writes into first-party durable files (e.g.,
02-DOCS/wiki/harness/user-profile.md, rootCLAUDE.md)—so outsider-authored free text can be submitted via the chat context the workflow harvests.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata