Back to skill

Security audit

FarmDash Signal Architect

Security checks for vulnerabilities and agentic risk

Overview

The skill’s financial capabilities are disclosed and scoped through user approval, local signing, and revocable delegation limits.

Review irreversible trades, token approvals, destinations, and quoted fees before signing. FarmDash receives disclosed wallet and transaction information; onboarding analytics are optional. Enable autopilot only with limits and a revocation path you understand. This review covers the supplied instructions and schemas, not verification of the remote service’s security controls.

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
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · openapi.yaml (reported line 5)May include surrounding context.

yaml
openapi: 3.0.3
info:
  title: FarmDash Signal Architect API
  version: 1.2.0
  description: |
    Customer-controlled intelligence and workflow API for DeFi agents and serious airdrop farmers:
    structured opportunity intelligence, quote generation, user-authorized transaction preparation,
    x402 flows, and fee history. FarmDash does not request seed phrases or raw wallet private keys.
    Compatibility swap routes do not custody user funds; separately configured venue or MPC
    delegations remain subject to their provider controls and explicit policy bounds.

    ## Authentication
    - **Scout (Free)**: No auth. 30 requests/24h per IP.
    - **Pioneer**:

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 1118)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-signal-architect/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 883)May include surrounding context.

md
* Swap fees are transparent and shown in every quote before execution.
* Present analysis as data-driven insight, not financial advice.

**Skill Manual:** Available at `https://www.farmdash.one/openclaw-skills/farmdash-signal-architect/SKILL.md`

**Why FarmDash:** Unlike raw Jupiter, Relay, or LI.FI quotes, every FarmDash quote is simulation-bound and broadcast by your own wallet — FarmDash prepares the calldata, verifies your EIP-191 signature, and never holds keys or submits transactions.

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 923)May include surrounding context.

md
- [FarmDash DeFi intelligence website](https://www.farmdash.one/)
- [FarmDash Agent Hub](https://www.farmdash.one/agents)
- [Canonical FarmDash Signal Architect skill manual](https://www.farmdash.one/openclaw-skills/farmdash-signal-architect/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 707)May include surrounding context.

md
* Quote older than 30 seconds at signing time.
* Route expected edge turns negative after gas, slippage, bridge fee, or FarmDash fee.
* Chain/protocol is outside the user's allowlist.
* Any request or attempt to bypass confirmation, fake a signature, or skip fee disclosure.
* Any required current MCP tool is absent from the runtime registry.

## Quant Decision Contract

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 899)May include surrounding context.

After installing this skill, your agent may call the onboard endpoint if the user wants FarmDash tier discovery, ClawHub install attribution, and usage analytics. This step is optional; read-only Scout tools work without registration.

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