Back to skill

Security audit

AgentLine

Security checks for vulnerabilities and agentic risk

Overview

AgentLine operations have clear approval controls, but setup directs the agent to execute downloaded software without separate installation approval or a defined installation scope.

Review the setup path before installing. Install a verified CLI release yourself, or require approval after reviewing the installer and its local changes. AgentLine data passes through OOMOL, and deleting an agent permanently removes associated records. Keep the existing write and deletion confirmations. The remote installer remains outside the verified artifact.

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 code performs remote script execution for an apparent Oomol CLI installation, not AgentLine data operations. Installing a dependency could be a supporting implementation detail, but the supplied content establishes no connection between this installer and AgentLine. The remote script's contents and any further effects are not available for assessment.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command streams a mutable remote script directly into Bash without integrity verification or an opportunity to review the downloaded artifact; the PowerShell alternative has the same weakness. Although the domain is relevant to the documented integration and setup runs only when needed, compromise of the distribution endpoint could execute arbitrary code with the invoking user's privileges.

Content

Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

The setup workflow executes downloaded installation scripts without warning the user about local code execution and system changes.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

When the CLI is missing, the setup instructions direct the agent to execute a downloaded installer without separately obtaining approval for local software installation or explaining its system changes. This is outside the AgentLine write/destructive-action confirmation rules; the conditional setup trigger reduces exposure, and the declared tool allowlist may block installation, but neither provides explicit installation consent.

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 89)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