perplexity-search

Warn

Audited by Snyk on Jul 29, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow posts user-provided query/recency into POST https://pplx.x402.paysponge.com/search and then ingests the returned page content/snippets to synthesize an answer, which originates from outsider-authored web pages.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

  • Direct money access detected (high risk: 1.00). The skill is explicitly wired to a payment rail: calls are compiled into selat-pay and settled in USDC on Base (Circle Gateway). The manifest and workflow instruct running selat-pay (paid runs settle funds), mention gateway settlement behavior, and require telling the user the cost before spending. This is a specific crypto/payment integration (wallet/settlement) capable of initiating real payments, so it grants direct financial execution authority.

Issues (2)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W009
MEDIUM

Direct money access capability detected (payment gateways, crypto, banking).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 29, 2026, 07:34 PM
Issues
2
Security Audit — snyk — perplexity-search