Back to skill

Security audit

Tanium

Security checks for vulnerabilities and agentic risk

Overview

The Tanium workflow requires confirmation for changes, but its setup can execute unverified downloaded code without a separate approval step.

Review the setup before installing. Install a reviewed CLI release deliberately, check its automatic skill synchronization settings, and connect a Tanium account with only the permissions needed. Retain confirmation for every GraphQL operation. The remote installer and hosted connector implementation were not verified.

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 chunk performs remote script execution for an Oomol CLI installer, not Tanium data operations. Although installing dependencies can be a supporting implementation detail, nothing supplied establishes this installer as a Tanium dependency. The downloaded script's contents and subsequent effects are not available for assessment.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an unpinned HTTPS response directly into Bash executes its contents with the invoking account's privileges without prior verification. The endpoint is relevant to the documented CLI dependency, but a compromised host or installer release could still execute malicious code and access local files or credentials; HTTPS alone does not establish installer integrity.

Content

Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.

Setup instructs the agent to execute downloaded installation scripts without warning about local system changes or remote-code execution.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The fallback setup tells the agent to execute remotely downloaded shell or PowerShell code without an explicit installation approval or integrity-verification step. Although conditional on the CLI being missing and serving a legitimate dependency, this can expose the local account to arbitrary code if the installer delivery path is compromised; the declared tool restriction may limit execution but is not a substitute for safe instructions.

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 76)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