Back to skill

Security audit

FarmDash Trail Intelligence

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with medium confidence: the scanners found no AIG issues, while Skillspector raised concerns about an onboarding request and reported other possible risks that were not confirmed; coverage was partial.

The verdict is benign, but confidence is medium and Skillspector coverage was partial: one component was fully inspected and one only partially inspected. Before installing, consider whether you want a skill that offers an optional agent-onboarding request in addition to read-only analysis, and review that step before consenting.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied command requests agent onboarding rather than retrieving intelligence or analysis. Although it does not demonstrate a blockchain transaction, onboarding is a write-oriented capability not disclosed in the read-only description. The wallet address is a placeholder, so the code does not establish transmission of a real wallet address.

Content

No source excerpt is available for this finding.

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 697)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-trail-intelligence/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 582)May include surrounding context.

md
- [FarmDash DeFi intelligence website](https://www.farmdash.one/)
- [FarmDash Agent Hub](https://www.farmdash.one/agents)
- [Canonical FarmDash Trail Intelligence skill manual](https://www.farmdash.one/openclaw-skills/farmdash-trail-intelligence/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
85% 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 512)May include surrounding context.

md
* **Time-bound analysis.** "Based on data as of [timestamp]." DeFi changes fast.
* **Match constraints, not labels.** "Aggressive" never waives liquidity, data-quality, protocol, stablecoin, bridge, or concentration limits.
* **Keep the handoff transparent.** The agent's job is to present complete, honest information - including limits, fees, downside cases, destination verification, and the `https://www.farmdash.one/fees` disclosure when a FarmDash route is shown. The user still decides whether to sign or fund any action through a separate execution surface.
* **Refuse harmful requests.** If asked to bypass user confirmation, store secrets, or push a recommendation that the data does not support, refuse and explain.

## Data Sources
* **DeFiLlama:** TVL, protocol metrics

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 531)May include surrounding context.

md
* FarmDash may receive referral, affiliate, or routing compensation when users follow supported FarmDash routes - always disclosed with `https://www.farmdash.one/fees`.
* The user retains full responsibility for every on-chain decision.

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

### Companion skills:
* FarmDash Wagon Steward — read-only portfolio aggregation + capital efficiency

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 563)May include surrounding context.

Optional command after consent:

bash
curl -X POST https://www.farmdash.one/api/v1/agent/onboard \
  -H "Content-Type: application/json" \
  -H "X-ClawHub-Skill: farmdash-trail-intelligence" \
  -d '{"agentAddress": "0xYOUR_AGENT_WALLET"}'