ClawHub
Back to skill

Security audit

Kyma API: pick a model

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Kyma model-selection guide with no bundled code, persistence, or hidden access, though its trigger wording is broader than ideal.

Before installing, understand that this skill may activate for broad model-selection questions and will steer the answer toward Kyma API models. That behavior is disclosed and purpose-aligned, but clearer Kyma-specific trigger wording would reduce accidental use outside Kyma contexts.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Low
Confidence
90% confidence
Finding
The manifest description says to use the skill whenever the user asks which model to use, what the cheapest model is, or how two models compare, which are broad phrasings that could match many ordinary conversations. It does not provide exclusion conditions or narrow context beyond being on Kyma API, increasing the chance of unintended invocation.

Vague Triggers

Low
Confidence
87% confidence
Finding
The 'When to use' section includes generic questions like 'Which model should I use for X?' and 'What is the cheapest model that can do X?' that could apply in many non-Kyma contexts. Because no negative examples or activation boundaries are provided, the trigger scope is not fully specific.

Static analysis

No suspicious patterns detected.