Back to skill

Security audit

Unipile

Security checks for vulnerabilities and agentic risk

Overview

The Unipile features fit the stated purpose, but automatic setup executes unverified downloaded code and leaves broader installation effects unexplained.

Review and install a verified CLI release yourself before enabling this skill, and check its automatic skill-installation settings. Connect only the Unipile accounts you intend to expose through OOMOL. The review concern is uncontrolled setup and under-disclosed agent changes; no malicious intent or exfiltration was established. The remote installers were unavailable for inspection.

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 (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied code performs remote installer execution rather than searching or reading Unipile data. It accesses an Oomol endpoint and provides no evidence that this installation supports the declared Unipile functionality. The downloaded script's contents and further effects are not available for assessment.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
87% confidence
Finding

Authentication can support a data-access skill, but it is the entire behavior shown here, with no demonstrated connection to Unipile or subsequent data access. The supplied chunk therefore has a materially different primary purpose. The command alone does not establish which service is authenticated or how credentials are handled.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an HTTPS response directly into bash executes mutable remote content without review, version pinning, or publisher verification beyond transport security. If the installer endpoint or its publishing infrastructure is compromised, the command can run attacker-controlled code with access to local files and credentials; this is the same underlying installation risk highlighted by SQP-2.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

The setup workflow executes remotely downloaded installation scripts without warning the user about the system-integrity implications.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The missing-CLI fallback directs execution of downloaded shell or PowerShell scripts without an explicit approval step or independent integrity verification. A compromised installer distribution path could execute arbitrary code with the invoking user's privileges; limiting installation to a missing dependency reduces exposure but does not eliminate this risk.

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 81)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