Polygon Agent
Fail
Audited by Snyk on Jun 24, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.80). The prompt explicitly requires the agent to output raw, untruncated approval/funding URLs (which contain relay request IDs/tokens) verbatim to the user, forcing reproduction of potentially sensitive tokens in the model output.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The required runtime workflow for x402 calls (
polygon-agent x402-pay→ endpoint returns 402 → CLI retries and returns response text) can ingest outsider-authored free text from public web/API responses (e.g., article extraction, web search, news, Twitter/X data) into the agent’s LLM context via the returned payload.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs the agent at runtime to fetch and "load the relevant sub-skill" from remote SKILL.md files (e.g. GET https://agentconnect.polygon.technology/polygon-discovery/SKILL.md and the related https://agentconnect.polygon.technology/polygon-defi/SKILL.md and https://agentconnect.polygon.technology/polygon-polymarket/SKILL.md), which would directly control agent prompts/instructions.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). The skill explicitly provides crypto financial execution capabilities: it manages private keys/sessions (builder.json contains privateKey), creates and funds wallets, and exposes commands that send value and interact with blockchains (polygon-agent send / send-native / send-token, swap, deposit, withdraw, fund, x402-pay). It supports broadcasting transactions (--broadcast), direct EOA transfers (--direct), EIP-3009 signed payments (x402-pay), and deposit/withdraw to DeFi protocols. These are specific tools to move money and sign blockchain transactions, so this skill grants direct financial execution authority.
Issues (4)
W007
HIGHInsecure credential handling detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata