Back to skill

Security audit

FarmDash Ledger Keeper

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign because the reported behavior appears aligned with ledger review and accounting; confidence is medium, and the scan was partial because two local references could not be resolved.

The verdict is benign, not risk-free. Before installing, consider whether you are comfortable using a skill for ledger and transaction reporting, and review its instructions and any remote copy you obtain. The scan inspected both listed components but remained partial because two local references could not be resolved, so it does not provide complete evidence.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

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 102)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-ledger-keeper/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 118)May include surrounding context.

md
- [FarmDash DeFi intelligence website](https://www.farmdash.one/)
- [FarmDash Agent Hub](https://www.farmdash.one/agents)
- [Canonical FarmDash Ledger Keeper skill manual](https://www.farmdash.one/openclaw-skills/farmdash-ledger-keeper/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
75% 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 53)May include surrounding context.

md
A transaction hash counts as broadcast, not confirmation. Only `settlement_status: confirmed` counts as a confirmed spot event. Futures notional includes submitted `order_submitted` events only and is not a fill, exposure, or P&L measure.

### Confirmation Gate Before Counting Results
Count only `settlement_status: confirmed` rows as confirmed spot events; treat hashes without confirmation as broadcast-only; treat futures `order_submitted` rows as submission counts with estimated notional only; do not mix ledger review with execution confirmation; never infer fills, confirmation, tax treatment, or venue tax lots from protocol labels or unconfirmed rows.

### `ledger_tax_export`

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 101)May include surrounding context.

md
### Report-Back Template — Activity / Costs / Invalidation / Records
Report: agentAddress + start / end; confirmed vs broadcast spot counts with `realizedPnlUsd: null` stated plainly; recorded costs; futures `order_submitted` notional labeled not-a-fill; invalidation (any missing fill, fee, funding, or basis input means no realized P&L claim); reconciliation residual vs Wagon Steward view; and CSV availability via `ledger_tax_export` (agent address, date, protocol, from/to tokens, volume, recorded cost, tx hash, chain id) for professional review.

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

**Companion skills:** FarmDash Signal Architect, FarmDash Futures Strategist, FarmDash Wagon Steward, FarmDash Trail Marshal.