ClawHub
Back to skill

Security audit

Kyma API: send a test completion

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrowly scoped guide for running user-approved, billed Kyma model test completions and reporting cost and output.

Install only if you intend to let the agent make real billed Kyma API test calls. Before each call, verify the exact model, prompt, estimated cost, and that the agent asks for fresh explicit approval.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Anti-Refusal Statement

High
Category
Anti-Refusal
Content
## Comparing models

Run the same prompt against each model as separate approved calls, with the same `max_tokens`. Put the replies side by side with each one's cost and latency. Do not judge a model on a single short completion — say what the sample does and does not show.

## Do not
Confidence
85% confidence
Finding
Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Static analysis

No suspicious patterns detected.