memory-management
Warn
Audited by Snyk on Aug 14, 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). The skill’s runtime workflow ingests outsider-authored free text via the MCP/CLI “query” parameter (task intent) and uses it to decide whether to retrieve and then read project memory files, in particular when invoked through the MCP server’s
memory_autotool and hook preflight path.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata