ClawHub
Back to skill

Security audit

Agentar

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to be a coherent CLI helper, but users should treat its install and credential examples as security-sensitive.

Install only if you trust the CLI publisher and the installer source. Prefer downloading and inspecting the installer, verifying checksums or signatures if available, and avoid putting API keys directly in shell history. Store tokens with restrictive permissions, use environment or secret-manager handling where practical, and know how to revoke and delete credentials after use.

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 (2)

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The instructions recommend piping a remotely downloaded shell script directly into bash, which executes unverified code with no integrity check, signature verification, pinning, or review step. In a CLI-installation skill, this is especially dangerous because users are likely to copy-paste the command verbatim, so a compromised server, MITM in a misconfigured environment, or replaced artifact could lead to arbitrary code execution on the host.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The authentication examples encourage use of API keys and persistent token/state files without any guidance on secure handling, file permissions, cleanup, shell history exposure, or secrets management. In an agent-delegation CLI context, these credentials may grant access to external services or user data, so insecure examples can lead to credential leakage or unintended persistence on shared systems and CI runners.

Static analysis

No suspicious patterns detected.