Back to skill

Security audit

crypto-coin-check

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because it reports sharing trade details with an external provider without a privacy notice and allowing paid requests without prior user approval.

Before installing, consider whether you are comfortable sharing your asset of interest and exact trade size with an external provider, and whether the skill may make paid requests without asking first. The scan covered the listed component and completed successfully; its findings describe privacy and spending-consent concerns, not a claim of malicious intent.

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 (2)

The workflow sends the user's trade size to AgentReeve without a privacy warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The workflow transmits the user's asset of interest and exact intended trade size to an external provider without an explicit privacy notice or consent check. These details can reveal sensitive trading intentions, particularly if requests are linked to a payment wallet; however, the transmission supports the advertised liquidity calculation rather than indicating covert exfiltration.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
88% confidence
Finding

The skill grants itself permission to spend up to $0.25 per task without establishing that the user has authorized paid requests. The low cap and recipient, network, and asset checks substantially limit exposure, but they do not establish spending consent or prevent costs accumulating across tasks.

Content

Scanner excerpt · SKILL.md (reported line 25)May include surrounding context.

md
## Paying safely (read before any paid call)
- A paid call first answers HTTP 402 with a quote. Pay only if the quote's `payTo` is **0xDeA94ef76afa86bf1638B645F76108dF65890c0b**, the network is Base (`eip155:8453`) and the asset is USDC. Otherwise stop and tell the user.
- Spend at most **$0.25 per task** without asking. Above that, tell the user the total and wait for approval.
- If you have no x402 wallet, use the free sample and say that live data needs an x402-capable client.
- HTTP 503 or an error means no fresh data: say so. **Never invent or estimate numbers.** Failed calls are never charged.
- This is observational market data, not financial advice. Say so when relaying it.