Back to skill

Security audit

FarmDash Hedge Warden

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because it may send portfolio exposure to FarmDash without clearly warning users; the scan was partial, so its evidence is incomplete.

Before installing, consider whether you are comfortable sharing portfolio exposure with FarmDash. The scan was partial because some local references could not be resolved, so the evidence does not cover everything.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.json (reported line 111)May include surrounding context.

json
"links": {
    "website": "https://www.farmdash.one/",
    "agentHub": "https://www.farmdash.one/agents",
    "canonicalSkill": "https://www.farmdash.one/openclaw-skills/farmdash-hedge-warden/SKILL.md",
    "documentation": "https://www.farmdash.one/docs",
    "status": "https://www.farmdash.one/api/v1/agent/status",
    "openApi": "https://www.farmdash.one/agents/openapi.yaml",

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 96)May include surrounding context.

md
Hedges can lose money, over-hedge, under-hedge, or fail during volatile markets. Funding, liquidation risk, basis, and venue risk can erase yield. This skill is not financial advice.

**Install:** Copy this file into your OpenClaw workspace, or fetch `https://www.farmdash.one/openclaw-skills/farmdash-hedge-warden/SKILL.md`.

**Companion skills:** FarmDash Futures Strategist, FarmDash Wagon Steward, FarmDash Supply Master, FarmDash Camp Guard.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 113)May include surrounding context.

md
- [FarmDash DeFi intelligence website](https://www.farmdash.one/)
- [FarmDash Agent Hub](https://www.farmdash.one/agents)
- [Canonical FarmDash Hedge Warden skill manual](https://www.farmdash.one/openclaw-skills/farmdash-hedge-warden/SKILL.md)
- [Agent integration documentation](https://www.farmdash.one/docs)
- [Live agent capability status](https://www.farmdash.one/api/v1/agent/status)
- [OpenAPI contract](https://www.farmdash.one/agents/openapi.yaml)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 22)May include surrounding context.

md
proval for every order/cancel and a local Hyperliquid EIP-712 venue signature through Futures Strategist.
- **BOUNDED_AUTONOMOUS** may run without per-order human confirmation only under a valid owner-signed futures grant, current API-wallet venue authority, and all session, binding, scope, policy, risk, budget, builder and replay checks. Every venue action still needs a local signature.
- Read futures bounded readiness in the generated canonical table and live status. Bounded hedges may not be automatically executed while a runtime gate is closed. Spot grants, generic session policy, paid access and a hedge recommendation never create futures authority.
- Discover through `POST /api/v1/agent/authority`, `action: get_futures_authority`, `sessionId`, `sessionToken`; revoke the actual grant using `action: revoke_futures_policy`, `grantId`, `sessionId`, `sessionToken`. These are authority REST actions, not new Hedge Warden tools. Hand the selected `executionMode`, `grantId`, `sessionId`,

The workflow sends portfolio exposure to FarmDash without warning the user about this financial-data disclosure.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The workflow directs the agent to obtain portfolio exposure and submit it to FarmDash's hedge-recommendation service without explicitly disclosing that financial information leaves the user's environment. Asset holdings and notional values are sensitive, and authenticated requests or persistent installation identifiers can make submissions linkable; the advisory-only restriction does not protect data confidentiality.

Content

No source excerpt is available for this finding.