donation-place-search
Warn
Audited by Snyk on May 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's workflow (see SKILL.md, Workflow step 3) explicitly instructs the agent to open or cite best-effort external verification links (e.g., https://www.1365.go.kr/dntn/main.do) and to use charity homepage URLs returned by the helper, meaning the agent will read/interprete open public third-party pages whose content can alter verification and recommendation decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata