ClawHub
Back to skill

Security audit

Crypto Market Data

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward crypto market-data helper, with minor packaging and file-output caveats but no evidence of hidden or malicious behavior.

Install only if you are comfortable with an agent fetching public crypto market data and optionally writing JSON files you request. Check the package contents before relying on it, because the inspected artifact references a bundled Node script and reference file that were not included.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description says to use the skill when a user asks to get crypto realtime data, historical candles, full price history, Binance spot data, CoinGecko market-chart data, or wants to reuse market data in another project. This is a wide natural-language trigger surface with no exclusion conditions or negative examples, so it may overlap with many ordinary crypto-related requests and cause unintended invocation.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 82)May include surrounding context.

node ~/.codex/skills/crypto-market-data/scripts/fetch-market-data.mjs BTC --history --history-source coingecko --coin-id bitcoin --range max

text

Write JSON to a file:

```bash
node ~/.codex/skills/crypto-market-data/scripts/fetch-market-data.mjs TRUMP --realtime --history --range 30d --out trump-market.json

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest description frames the skill as a data-fetching utility for realtime and historical crypto prices. In SKILL.md, the documented --out usage shows the skill can also persist data to disk, which is a behavior beyond pure retrieval and reuse-in-memory.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The documentation instructs users to write JSON to a file without explicitly warning that this modifies the local filesystem. In agentic environments, even benign file writes can have unintended effects if users are not clearly informed or if output paths are chosen unsafely.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.