ClawHub
Back to skill

Security audit

Claude Hemat

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple model-routing instruction file and does not contain hidden code, persistence, credential handling, or destructive behavior.

Before installing, understand that this skill is meant to route work to specific Claude-family models and may send full task descriptions to more advanced Anthropic model sessions when available. It appears benign, but users who want strict control over provider usage or cost should review the model-routing rules first.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 28)May include surrounding context.

md
2. Casual chat - No reasoning needed
3. Quick lookups
4. File lookups
5. Simple tasks - May but not limited to repetitive tasks
6. Cron Jobs, if it needs reasoning, THEN ESCALATE TO THE NEXT ADVANCED MODEL
6. Basically everything that doesn't need any thinking
7. Provide concise output, just plain answer, no explaining

Static analysis

No suspicious patterns detected.