tavily-hikari-search
Warn
Audited by Snyk on Jul 15, 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 workflow runs
tvly-hikari search ... --json, which fetches public web search results at runtime and then the agent “summarize[s] from the JSON result,” meaning outsider-authored web content/metadata is ingested into the LLM context via the search JSON.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata