add-karpathy-llm-wiki
Warn
Audited by Snyk on Jun 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The required workflow reads and ingests user-provided sources into the wiki (e.g., files/URLs dropped into
groups/<group>/sources/), and those sources are outsider-authored free text that the agent then reads and converts into LLM-readable markdown for updatingwiki/andindex.md/log.md.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata