ClawHub
Back to skill

Security audit

Knock

Security checks for vulnerabilities and agentic risk

Overview

Knock changes require approval, but the required CLI can also install other agent skills without this skill explaining or controlling those changes.

Review the CLI's automatic skill installation before using this integration. If those changes are unwanted, configure OO_SKILLS_SYNC_DISABLED=1 before any oo invocation. Verify the installer and select a reviewed CLI version separately. OOMOL mediates access to your connected Knock account; retain the skill's explicit approval checks for updates, workflow triggers, and permanent deletion. The remote installers and hosted connector implementation were not verified.

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
95% confidence
Finding

The supplied code performs remote installer execution rather than any visible Knock operation. No evidence in the chunk establishes that this installer is a supporting dependency for Knock. The downloaded script is 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
99% confidence
Finding

The setup command pipes a remotely retrieved, unpinned script directly into Bash without integrity verification or review; the Windows alternative uses the equivalent fetch-and-execute pattern. If the installer endpoint or its delivery infrastructure is compromised, attacker-controlled code executes with the invoking user's privileges and could access local files or credentials. The legitimate CLI dependency and missing-command condition explain the purpose and limit exposure, but do not remove this supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 59)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 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