ClawHub
Back to skill

Security audit

AgentBox Sandbox

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only AgentBox help skill with some credential-handling examples users should treat carefully, but no hidden code or automatic access.

Install only if you want AgentBox documentation help. Do not paste real passwords into command-line examples or hardcode real API keys in source files; use interactive login, environment variables, or a secret manager where possible.

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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The documentation shows agentbox auth login -u your_email -p your_password, which encourages passing a password directly on the command line. CLI arguments are often exposed via shell history, process listings, logging, or telemetry, so users may unintentionally leak credentials. In a support skill intended to guide real users, this example is especially risky because it is likely to be copied verbatim.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The Python example hard-codes an API key string in sample code, which normalizes embedding secrets directly in source files. Users often copy examples into repos, notebooks, or shared snippets, causing accidental credential exposure through version control, logs, or screenshots. Because this skill is a docs summary for operational use, the chance of unsafe copy-paste is relatively high.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The quickstart pattern tells the skill to explain how to authenticate or set an API key, and later examples include api_key and environment-variable usage. The file recommends scoped env vars for secrets, but it does not clearly warn users not to expose real credentials in prompts, code samples, logs, or shared files.

Content

No source excerpt is available for this finding.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
references/agentbox-official.md:54

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:87