ClawHub
Back to skill

Security audit

Waterfall

Security checks for vulnerabilities and agentic risk

Overview

The Waterfall workflow is coherent, but its installer and undisclosed changes to other agents’ skills warrant review.

Review and install a verified CLI release yourself before use. If you do not want additional agent skills installed or refreshed, set OO_SKILLS_SYNC_DISABLED=1 before invoking the CLI, as documented in the [publisher reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md). Connect only the intended Waterfall account and review write payloads. The remote installers were unavailable for inspection; this review does not establish their contents or the hosted service's implementation.

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 command executes an Oomol CLI installer, with no visible Waterfall integration or data operations. Nothing in the supplied chunk establishes this installation as a supporting dependency for the declared purpose. The remote script's contents are not supplied, so its additional behavior cannot be assessed.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The setup command immediately executes a remotely downloaded script without version pinning or independent integrity verification; the PowerShell alternative has the same weakness. Compromise of the distribution endpoint or its release pipeline could execute arbitrary code with the invoking process's privileges, exposing local files and credentials. Limiting installation to a missing-CLI error reduces exposure frequency but does not make the downloaded code trustworthy.

Content

Scanner excerpt · SKILL.md (reported line 61)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 82)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