Back to skill

Security audit

HyperGrok Hyperliquid Positions

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill benign because the reported external requests appear consistent with its stated purpose, though the review is incomplete and overall confidence is medium.

The verdict is benign with medium confidence, not a guarantee of safety. Before installing, consider whether you are comfortable with the reported external API requests and the unresolved local references; the scanner did not fully complete its analysis.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 31)May include surrounding context.

bash
ADDR=$HYPERLIQUID_ACCOUNT_ADDRESS
BASE=$([ "$HYPERLIQUID_NETWORK" = mainnet ] && echo https://api.hyperliquid.xyz || echo https://api.hyperliquid-testnet.xyz)
curl -sS -X POST $BASE/info -H 'Content-Type: application/json' -d "{\"type\":\"clearinghouseState\",\"user\":\"$ADDR\"}" | jq '{
  accountValue: .marginSummary.accountValue, totalMarginUsed: .marginSummary.totalMarginUsed,
  withdrawable, crossMaintenanceMarginUsed,
  positions: [.assetPositions[].position | {coin, szi, entryPx, positionValue, unrealizedPnl, liquidationPx, marginUsed,

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 43)May include surrounding context.

Margin tiers for a market:

bash
curl -sS -X POST $BASE/info -H 'Content-Type: application/json' -d '{"type":"meta"}' \
 | jq --arg c ETH '(.universe[] | select(.name==$c)) as $u | ($u.marginTableId // $u.maxLeverage) as $id
      | {name:$u.name, szDecimals:$u.szDecimals, maxLeverage:$u.maxLeverage, marginTableId:$id,
         tiers: (if $id < 50 then [{lowerBound:"0.0", maxLeverage:$id}]

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 109)May include surrounding context.

A position is protected when a reduce-only trigger order on the opposite side is resting on the exchange, either sized at least to the position or position-tied (sz: "0.0", isPositionTpsl: true, meaning "the whole position"). Verify with frontendOpenOrders, which exposes trigger fields:

bash
curl -sS -X POST $BASE/info -H 'Content-Type: application/json' -d "{\"type\":\"frontendOpenOrders\",\"user\":\"$ADDR\"}" \
 | jq '[.[] | select(.isTrigger==true) | {coin, side, sz, triggerPx, triggerCondition, orderType, reduceOnly, isPositionTpsl, oid, cloid}]'