Back to skill

Security audit

go-cerebras

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Go client guide for using Cerebras APIs, with disclosed API-key and network use that fits its purpose.

Before installing, confirm you trust the upstream Go module and use a Cerebras API key stored in the environment, not in source code. Avoid logging request headers or prompts, and remember that prompts sent through the client go to the configured Cerebras API endpoint.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

This markdown file documents adding a Bearer token from CEREBRAS_API_KEY to outgoing HTTP requests, which affects user credentials/privacy. The setup guide does not include any warning or disclosure about sending the API key to an external service or advising users to protect and scope the credential.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.