ClawHub
Back to skill

Security audit

Buildin CLI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed guide for using the Buildin CLI with sensible approval, authentication, credential-handling, and write-safety controls.

Before installing, confirm you trust Buildin and only approve installer, update, login, upload, create, or update actions for the exact workspace and content you intend. Do not paste bearer tokens into chat; use environment variables, saved credentials, or an approved secret channel.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 26)May include surrounding context.

md
Use the Buildin CLI (`buildin`) for Buildin V2 API work: pages, blocks,
databases, search, Markdown content, and files.

The CLI source repository may be private. Do not ask the user to clone source
code before using the CLI. Install or update the released binary from the
official Buildin CDN only after the user explicitly approves it.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 139)May include surrounding context.

md
This is CLI resolution behavior, not authorization to expose a credential. Do
not pass `--token` in agent commands, logs, or shared shells: it can leak via
process listings or shell history. Do not ask users to paste bearer tokens into
chat. Use preconfigured `BUILDIN_TOKEN`, saved credentials, or an approved secret
channel; redact any credential that appears in command output.

Static analysis

No suspicious patterns detected.