Back to skill

Security audit

Cashu Emoji

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small local CLI for encoding and decoding hidden emoji text, including Cashu bearer tokens, with the main risk being careful handling of decoded token values.

Installers should treat any decoded Cashu token as money: avoid posting it in chat transcripts, logs, screenshots, or issue reports. Prefer metadata-only handling when possible, and use npm ci with the included lockfile for reproducible dependency installation.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill decodes and surfaces Cashu bearer tokens, which are effectively spendable secrets. While the document later notes that a decoded cashu... token is a bearer asset, the high-level description and early workflow do not prominently warn that displaying, logging, or sharing decoded output can expose funds, so an agent or user could inadvertently leak value during normal handling.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
78% confidence
Finding

The note says to append a sentinel like " ok" after the emoji token in some messengers, but it does not clearly define the exact activation phrase, required format, or when the sentinel is necessary versus optional. This ambiguity can cause unintended or inconsistent skill invocation behavior across contexts.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
40% confidence
Finding

Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

Content

Scanner excerpt · package.json (reported line 46)May include surrounding context.

json
"access": "public"
  },
  "dependencies": {
    "@cashu/cashu-ts": "^3.4.1"
  }
}

Static analysis

No suspicious patterns detected.