research-lookup
Warn
Audited by Snyk on Jun 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: 0.85). The skill’s runtime path sends the user’s query to external research backends (Parallel Chat API / Perplexity via OpenRouter) and then ingests the returned free-form report text (
response.choices[0].message.content) into the agent context, which can include outsider-authored content from the web/other sources.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata