memory-import
Warn
Audited by Snyk on Jul 2, 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). Outsider free text is ingested from the user-supplied external input files/directories (e.g., ChatGPT export JSON
--source chatgpt --input ...and Claude Code local.mdfiles--source claude-local --input ...), which are then written into the agent’s knowledge-base/cold store as readable prose (e.g.,content/bodyfields) and later become LLM context via search/refinement workflows.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata