memory-research
Warn
Audited by Snyk on Jun 12, 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 skill’s Step 1 “Web Research” fetches public web pages/URLs at runtime and then ingests their readable text into the agent to synthesize and summarize, which is outsider-authored free text (public web content).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata