Back to skill

Security audit

Airmeet

Security checks for vulnerabilities and agentic risk

Overview

The Airmeet actions only read data, but setup directs the agent to execute downloaded software without verification or a clear approval step.

Prefer an independently reviewed oo installation, and require approval before running either downloaded installer. Airmeet access uses your OOMOL-connected account, so review its granted permissions. Also review the CLI's automatic skill installation behavior. The bundled instructions were fully inspected, but the external installer contents and exact system changes could not be 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 code performs remote script execution rather than searching or reading Airmeet data. Although installation can be a supporting implementation detail, the supplied chunk establishes no connection between this installer and the declared Airmeet functionality. The downloaded script's contents and any further effects are not visible and cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

Piping a mutable HTTPS response directly into Bash executes its contents without version pinning, independent integrity verification, or review. A compromised installer host or distribution pipeline could thereby execute attacker-controlled code with the user's privileges; the OOMOL dependency is legitimate context but does not eliminate this supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

The setup workflow executes downloaded installer scripts without warning about remote code execution or local system changes.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The fallback setup instructs the agent to execute downloaded shell or PowerShell code without first obtaining approval for local software installation or explaining its effects. Although this occurs only when the CLI is missing, it expands a read-oriented Airmeet task into arbitrary code execution with the executing user's privileges.

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 80)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