Back to skill

Security audit

SmartSuite

Security checks for vulnerabilities and agentic risk

Overview

The SmartSuite workflow has clear approval rules, but its setup instructions can execute downloaded software without a separate installation approval.

Review the CLI installation before enabling this skill. Prefer installing a verified release yourself and require approval for subsequent installation changes. OOMOL mediates access to your connected SmartSuite account, and its CLI may also install other agent skills. The bundled SmartSuite instructions require approval for record changes and deletions; external installer behavior remains 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
96% confidence
Finding

The supplied command performs remote installer execution rather than SmartSuite data operations. Nothing in the chunk establishes this installer as a supporting dependency for the declared purpose. The downloaded script is not supplied, so its subsequent actions and safety cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

Piping an HTTPS response directly into bash executes whatever the remote endpoint serves, without a pinned version, signature check, or opportunity for review. Compromise of the installer endpoint or its publishing pipeline could lead to local code execution, exposing files and credentials accessible to the agent; HTTPS alone does not protect against a compromised publisher.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

The setup workflow instructs the agent to execute downloaded installer scripts without warning the user about running remote code.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

The setup instructions direct the agent to execute remote installer code without requiring informed approval or integrity verification. Although this is a legitimate prerequisite and runs only when the CLI is missing, it can turn a routine SmartSuite request into local software installation with the agent process's permissions.

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 82)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