ClawHub
Back to skill

Security audit

go-skyvern

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Go client helper for Skyvern, with expected API-key and network use disclosed and no hidden execution or persistence found.

Install only if you intend to use Skyvern from Go. Treat `SKYVERN_API_KEY` as a secret, use the official Skyvern Cloud URL or a deployment you explicitly choose, and review any task, agent, script, credential, schedule, delete, or cancel operation before allowing it because those calls can affect external websites, account resources, and service credits.

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
  • 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
87% confidence
Finding

This markdown file instructs users to export SKYVERN_API_KEY and send it in the x-api-key header, but it does not include any warning about protecting the credential, avoiding exposure in logs, or the sensitivity of transmitting it to the service. Because SQP-2 applies to markdown files, omission of a warning around credential-handling behavior is a valid documentation safety gap.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.