able-markets
Warn
Audited by Snyk on May 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's workflow includes concrete GitHub polling that fetches and decodes public proposal files (see poll.clj's fetch-github-file/check-aptos-proposal and the "GitHub Status Polling" code in SKILL.md which call api.github.com/repos/.../contents/...), and the agent parses those untrusted, public repo contents to determine proposal status and drive oracles/trading decisions—allowing third-party content to materially influence actions.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). The skill is specifically a financial/trading skill for prediction markets (not a generic tool). It includes explicit market-order functions (e.g., AbleMarket.buy_yes and buy_no), trading signals (cross_ecosystem_signal returning BUY recommendations), portfolio allocations/Half-Kelly bet sizing in APT, and on-chain market references (APT, Move multi-sig oracle, on-chain WEV). These are concrete, finance-specific capabilities for buying/allocating assets and running market simulations, so it meets the "market orders / crypto" criterion for direct financial execution risk.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata