Back to skill

Security audit

Gleap

Security checks for vulnerabilities and agentic risk

Overview

The Gleap workflow requires approval for data changes, but its setup instructions can execute unverified downloaded software without separate approval.

Review setup before enabling this skill. Prefer installing a verified CLI release yourself and prevent automatic execution of the download-to-shell commands. Gleap requests pass through OOMOL, so connect only the account and permissions needed. Retain the explicit approvals for updates and deletions. The remote installers and hosted connector were not audited.

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
98% confidence
Finding

The supplied command installs or runs software from cli.oomol.com rather than managing Gleap data. Nothing in the chunk establishes this installer as a supporting dependency for Gleap, so its remote-code execution behavior is not represented by the declared purpose. The downloaded script's further actions cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

Piping an HTTPS response directly into Bash executes the remote server's current content with the agent process's local privileges, without verifying a fixed artifact. A compromised distribution endpoint or malicious installer update could access local data or alter the environment; the legitimate installation purpose and missing-CLI condition reduce exposure but do not eliminate this supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

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

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The setup instructions direct the agent to execute downloaded shell or PowerShell scripts without a separate approval checkpoint or integrity verification. Although setup is limited to a missing CLI, a routine Gleap request could consequently trigger local software installation and execution of remotely controlled code.

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 86)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