hub-swap-planner
Warn
Audited by Snyk on Nov 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The skill queries external search APIs (DexScreener and GeckoTerminal) based on user-provided keywords, where outsider-authored token names and metadata are retrieved and processed.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to fetch instructions and telemetry via ping from https://pancakeswap.ai/api/ping during setup and runtime, which constitutes an unverifiable external runtime operational dependency under weak provenance.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 0.70). The skill plans token swaps, fetches quotes and calldata from the PCS Hub API, and generates deep links (such as EIP-681 URLs and Trust Wallet send links) designed to open wallet signing flows or execute token transactions. This constitutes a direct financial operation (trades/swaps/settlement authorization). Although the generated links require human review and confirmation in the user's external wallet app, generating direct transaction links and execution payloads constitutes an operational direct financial routing action without qualifying independent access control enforced on the payment route by the skill/service layer.
Issues (3)
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