Back to skill

Security audit

Knack

Security checks for vulnerabilities and agentic risk

Overview

The Knack workflow has clear data-change safeguards, but its setup can execute unverified remote code without an installation approval step.

Review setup before enabling this skill. Install the CLI through a separately reviewed process and check whether you want its bundled-skill synchronization. Connect only the needed Knack account and retain approval for every write or deletion. The remote installer payload was unavailable for verification; no malicious intent was established.

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
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
97% confidence
Finding

The supplied code installs software from Oomol, with no demonstrated connection to Knack functionality. This is an undeclared capability involving an inconsistent external resource, rather than an established supporting implementation detail. The remote script's contents and any further actions are not available for assessment.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

Piping a remotely fetched installer directly into Bash executes mutable network-delivered code with the agent's local privileges, without a review or integrity-verification step. HTTPS protects transport but does not prevent a compromised distribution endpoint from serving malicious code; the missing-CLI condition limits exposure but not the potential impact, and the PowerShell example has the same weakness.

Content

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

The setup workflow executes remote installation scripts without warning about executing third-party code or modifying the local system.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The fallback directs the agent to install software by executing third-party scripts without first obtaining explicit approval for local system changes. Although this happens only when the CLI is missing, authorization to operate on Knack data does not necessarily authorize installing software on the host.

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