jaguar-strategy

Warn

Audited by Snyk on Jun 17, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.65). Outsider free text can enter via mcporter_call("strategy_get_clearinghouse_state", ...) and mcporter_call("leaderboard_get_markets"), whose returned JSON is treated as readable market/position text and then fed into the agent/DSL decision context (e.g., signals/reasons/positions), and those data originate from external on-chain/leaderboard sources not authored by the operating user.

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

  • Direct money access detected (high risk: 1.00). The skill is explicitly a trading strategy that configures and delegates on‑chain position management to a runtime. It requires setting a strategy wallet address in runtime.yaml, references on‑chain position opens/closes, and documents CLI/runtime commands that create the runtime (openclaw senpi runtime create), inspect DSL-tracked positions (openclaw senpi dsl positions / inspect), and mentions position creation/timeouts and DSL exits handled by the runtime. These are specific crypto/trading controls (wallet configuration + on‑chain position management), not generic tooling — 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
Jun 17, 2026, 07:43 PM
Issues
2
Security Audit — snyk — jaguar-strategy