ClawHub
Back to skill

Security audit

PredictLeads

Security checks for vulnerabilities and agentic risk

Overview

The PredictLeads queries fit the stated purpose, but setup can execute unverified installers and introduce broader agent changes without clearly explaining them.

Review and install the CLI separately before enabling this skill, and decide whether its automatic installation of other agent skills is acceptable. OOMOL will mediate your PredictLeads requests. The remote installers were unavailable for inspection, so their exact installation effects 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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied chunk performs no visible PredictLeads search or data retrieval. Instead, it executes an Oomol-hosted installer, with no demonstrated connection to the declared service. This is a materially different operation involving an inconsistent resource, rather than a demonstrated supporting implementation detail. The downloaded script's contents and further effects are not available for assessment.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command streams a mutable remote script directly into Bash without verifying its integrity or reviewing it before execution. Compromise of the installer distribution path could execute attacker-controlled code with the agent's local permissions; HTTPS and the legitimate vendor context reduce some risks but do not protect against a compromised publisher or distribution service.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

The setup workflow executes remote installation scripts without warning about their system-level effects.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

When the CLI is missing, the skill directs the agent to execute a downloaded installer without first explaining its effects or obtaining approval for local software installation. This expands a read-only data request into arbitrary code execution with the invoking user's permissions; the conditional setup requirement limits exposure but does not establish authorization.

Content

No source excerpt is available for this finding.

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 80)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