Back to skill

Security audit

GoSquared

Security checks for vulnerabilities and agentic risk

Overview

The GoSquared actions fit the stated purpose, but automatic setup executes unverified downloaded code without clear user approval.

Review setup before enabling this skill. Install a reviewed CLI release separately, require approval for installation, and disable automatic skill synchronization if unwanted. Connect only the GoSquared account and permissions needed. The review concern is uncontrolled setup and its broader effects; the inspected artifact does not establish malicious intent, and the downloaded installers remain unverified.

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
99% confidence
Finding

The supplied command performs remote script execution and appears intended to install a CLI. It contains no GoSquared search or read operation and establishes no connection between the installer and the declared GoSquared functionality. The downloaded script's contents are not supplied, so its further effects cannot be assessed.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a remotely fetched installer directly into Bash executes mutable network content without prior inspection or artifact verification. HTTPS protects transport but does not prevent a compromised distribution server or malicious installer update from executing code with the agent's privileges; the PowerShell setup has the same underlying risk.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

The setup workflow instructs the agent to execute remote installation scripts without warning about the system-integrity implications.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The fallback setup instructs the agent to execute downloaded shell or PowerShell scripts without an explicit approval gate, integrity verification, or explanation of local system effects. Although limited to a missing-CLI condition, this can turn a read-only analytics request into local code execution with the agent's privileges.

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 79)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