ClawHub
Back to skill

Security audit

Paradym

Security checks for vulnerabilities and agentic risk

Overview

Paradym actions have clear safeguards, but setup can execute unverified downloads and introduce undisclosed changes to other agent skills.

Review the CLI installation before allowing automatic setup. Its documented startup behavior can change skills in multiple agent applications; consider setting OO_SKILLS_SYNC_DISABLED=1 before running it, as described in the publisher's command reference. Use a narrowly scoped Paradym connection and retain confirmation for writes. The remote installer and hosted connector were not verified; no malicious intent is established.

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
98% confidence
Finding

The supplied command runs an Oomol installer, with no visible Paradym interaction or evidence that this installation supports Paradym access. This is a materially different operation involving an inconsistent resource. The remote script's contents are not supplied, so its further behavior cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The installation command pipes a mutable remote script directly into Bash without verifying its integrity or authenticity beyond HTTPS; the PowerShell alternative has the same execution pattern. If the distribution endpoint or delivery infrastructure is compromised, attacker-controlled code would execute with the agent process's local privileges and could access files or credentials. Its conditional use for legitimate dependency setup reduces exposure but does not eliminate the supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 65)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 86)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