Back to skill

Security audit

BTC Market Brief

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a Bitcoin market brief skill with no executable files and two concerns—broad activation guidance and permission to spend up to $0.25 per task without asking—so the verdict is suspicious.

Before installing, consider whether you want the skill to activate only for explicitly Bitcoin-related requests and whether you approve paid calls. The reported artifact was fully inspected, but a suspicious verdict means these concerns merit review; it does not establish 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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 activation guidance includes a generic request for “a quick status before deciding something,” without requiring Bitcoin-related intent.

Medium
Category
Trigger Abuse
Confidence
92% confidence
Finding

Although the skill is Bitcoin-focused, this activation condition overlaps with ordinary requests for status updates in unrelated domains. The instruction does not explicitly constrain these generic requests to Bitcoin, potentially causing unintended invocation of the market-brief workflow.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
94% confidence
Finding

The skill authorizes spending up to $0.25 per task without establishing that the user has approved paid access or delegated a spending budget. The recipient, network, and asset checks reduce payment-redirection risk but do not establish user consent; repeated tasks or recurring briefs could accumulate charges beyond the per-task limit.

Content

Scanner excerpt · SKILL.md (reported line 19)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.