ClawHub
Back to skill

Security audit

Crypto Trading Bot (BTC/ETH or choose any)

Security checks for vulnerabilities and agentic risk

Overview

The file is not malicious, but it bundles several unrelated agent capabilities, including skill editing, device approval, scheduling, and crypto bot rule generation, with limited scoping.

Review this package carefully before installing. It does not contain executable malware, but it combines multiple domains and includes actions that can change device access, skill files, scheduled behavior, and trading automation logic. Use it only if you intend to grant that breadth, and require explicit approval before approving devices, editing installed skills, scheduling checks, or producing deployable trading rules.

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
  • 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)

Self-Modification

High
Category
Rogue Agent
Confidence
89% confidence
Finding

The Skill Creator section explicitly instructs editing SKILL.md and resources, which is a self-modification capability. Allowing a skill set to guide creation or modification of other skills is dangerous because it can be used to introduce persistence, weaken safeguards, or propagate unsafe instructions into future agent behavior, especially when mixed with unrelated skills in the same file.

Content

Scanner excerpt · SKILLS.md (reported line 26)May include surrounding context.

md
* Understand concrete examples  
* Plan reusable contents (scripts, references, assets)  
* Initialize with templates  
* Edit SKILL.md and resources  
* Package for distribution

---

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest description for the embedded crypto_trading_bot uses broad, natural trigger language such as analyzing setups and turning ideas into rules, without clear scoping or invocation constraints. In a shared skill environment, this can cause over-broad activation or accidental invocation in unrelated financial conversations, increasing the chance the agent performs sensitive trading-adjacent actions or produces risky automation without deliberate user intent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.