academic-paper-search
Warn
Audited by Snyk on Jun 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). Outsider free text can enter the LLM via the Tavily fallback: the skill calls
mcp__tavily__tavily-search(...), which fetches and returns web page snippets/content from third-party academic sites (e.g., SSRN pages) that the agent then includes in its LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata