frontpage-vote
Warn
Audited by Snyk on Jun 26, 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 includes calling Frontpage’s public API endpoints (e.g.,
GET /api/proposalsandGET /api/proposals/{id}/comments) which return outsider-authored free-text fields like proposaltitle/bodyand commentbody, and those readable strings are typically placed into the agent’s LLM context for summarization/decision-making.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). The skill explicitly requires on-chain payments for actions: every vote, submission, and comment costs $0.01 USDC "paid via the Machine Payments Protocol (MPP)". The API examples show using mppx / tempo with privateKeyToAccount and Mppx.create, and the POST endpoints (POST /api/votes, POST /api/proposals/submit, POST /api/proposals/{id}/comments) perform a payment and return payer/voter wallet addresses and amountMicros. This is a specific crypto/payment integration (wallet signing / MPP) intended to move funds as part of the skill's primary operations — not a generic HTTP or browser tool. Therefore it grants direct financial execution capability.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata