Back to skill

Security audit

arkcli-code-example

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marked this skill suspicious because its documentation reportedly allows an active API key to be inserted into generated code and exposed through files or output.

Treat this as a review-level warning. Before installing, consider whether generated examples or output could contain a live API key; avoid using real credentials with it unless that substitution risk has been addressed. The scan covered all five listed components, but a complete scan cannot rule out every risk.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Automatic API-key substitution contradicts the explicit prohibition on real keys in generated output.

High
Category
Excessive Agency
Confidence
97% confidence
Finding

The documentation states that the active API key automatically replaces $ARK_API_KEY in code, while the command writes generated code to disk and prints it or returns it as JSON. This can expose a live credential through generated files, agent context, captured output, or downstream sharing; the later prohibition on real keys and the output directory's .gitignore entry do not prevent those disclosures.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.