memory-view
Warn
Audited by Snyk on Jun 27, 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 runtime workflow for
/memory-viewrunsscripts/scan-memory.tswhich reads on-disk~/.claude/projects/<slug>/memory/*.md(including outsider-authored content if those files were not authored by the operating user) and embeds that free text into the generated HTML report that the agent opens; this HTML content is then available in the agent’s LLM context via the opened report artifact.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata