Back to skill

Security audit

HasData

Security checks for vulnerabilities and agentic risk

Overview

The HasData workflow is coherent, but its setup can execute unchecked downloaded code and change other agent skills without clear user control.

Review before installing. Arrange CLI setup separately using a verified release and approve its local changes. Check or disable automatic synchronization of additional agent skills. OOMOL mediates HasData requests and account access. The entire bundled skill was inspected; the scanner's reference gaps were resolved, but downloaded installer behavior remains unverified. No artifact-backed evidence establishes malicious intent.

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
99% confidence
Finding

The supplied command executes an external installer, with no visible HasData search or read operation or demonstrated connection to HasData. This introduces remote code execution and an apparent installation capability not represented by the declared purpose. The fetched script is not supplied, so its further actions cannot be assessed.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The supplied chunk only invokes a CLI login command; it contains no HasData search or read operation and does not establish that oo authenticates to HasData. Although authentication could be a supporting implementation detail if that connection were demonstrated, the visible behavior does not substantiate the declared purpose.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command pipes a mutable HTTPS response directly into bash without a pinned version, integrity verification, or review. Compromise of the installer host or delivery infrastructure could therefore produce arbitrary code execution with the agent process's permissions; the conditional fallback limits exposure but does not remove this supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

Fallback setup executes remote installer scripts without warning about local system changes or third-party code execution.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The missing-CLI fallback directs installation through downloaded shell or PowerShell code without requiring explicit user approval or explaining local system changes. Although conditional setup is legitimate, executing a third-party installer can modify the environment and access files or credentials available to the executing account.

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 77)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