ClawHub
Back to skill

Security audit

Slab

Security checks for vulnerabilities and agentic risk

Overview

Slab changes require approval, but setup executes unverified downloads and omits the CLI’s automatic installation of additional agent skills.

Review the CLI installation and its automatic skill synchronization before use. Prefer a verified, pinned CLI installation, review or disable additional skill installation, and grant only needed Slab permissions. Keep the required approvals for changes and deletions. The bundled instructions were fully inspected, but the remote installers and hosted connector implementation remain unverified.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The supplied code executes an installer from an external domain rather than performing Slab data operations. Installation could be a supporting implementation detail if a relevant dependency were established, but the supplied content provides no such connection. The downloaded script is not included, so its further behavior cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The setup command downloads a mutable remote script and immediately executes it without version pinning, integrity verification, or review; the PowerShell alternative has the same weakness. A compromised distribution endpoint or malicious installer update could execute arbitrary code with the invoking user's privileges, potentially accessing local secrets or modifying files. The legitimate dependency and missing-CLI prerequisite limit exposure, but HTTPS alone does not establish the safety of the downloaded code.

Content

Scanner excerpt · SKILL.md (reported line 71)May include surrounding context.

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 92)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources