ClawHub
Back to skill

Security audit

Kraken.io

Security checks for vulnerabilities and agentic risk

Overview

This skill is coherent for operating Kraken.io through OOMOL, but it includes a conditional remote installer command that should be reviewed before use.

Install only if you are comfortable with OOMOL as an intermediary for Kraken.io actions. Prefer installing the oo CLI manually from official documentation with verification where possible, and do not let an agent run the remote installer automatically. Review and approve image optimization payloads because that action writes data and may consume account quota.

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

External Script Fetching

High
Category
Supply Chain
Confidence
95% confidence
Finding

The skill instructs the agent to install software by piping a remotely fetched script directly into a shell (curl ... | bash). This is dangerous because it executes unauthenticated, mutable remote content immediately, enabling arbitrary code execution if the server, transport, distribution pipeline, or DNS is compromised; in an agent context, this can turn a documentation step into full host compromise.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

Static analysis

No suspicious patterns detected.