Back to skill

Security audit

AIsa

Security checks for vulnerabilities and agentic risk

Overview

The AIsa integration is coherent, but its automatic setup can execute unverified downloaded code without a separate approval step.

Before use, install and verify a specific oo CLI release yourself and review its automatic skill synchronization. Allow only intended AIsa requests, account for usage charges, and retain approval for background jobs and destructive actions. The sole bundled file was fully inspected; the remote installers and hosted connector implementations remain unverified. No artifact-backed malicious behavior was found.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The supplied chunk is a remote installer invocation, with no demonstrated connection to AIsa or its data operations. Although dependency installation can be a supporting implementation detail, nothing supplied establishes this installer as an AIsa dependency. The downloaded script is not provided, so its specific actions cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The fallback pipes a remotely fetched, unpinned installation script directly into Bash without integrity verification or review; the PowerShell alternative has the same issue. Compromise of the distribution endpoint or its publishing infrastructure could execute attacker-controlled code with the agent's local privileges, exposing files and credentials. Limiting installation to a missing-CLI error reduces exposure but does not make the downloaded code trustworthy or establish permission to install software.

Content

Scanner excerpt · SKILL.md (reported line 227)May include surrounding context.

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 248)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