Back to skill

Security audit

JustCall

Security checks for vulnerabilities and agentic risk

Overview

The JustCall controls are appropriate, but setup can execute an unverified online installer without explicit approval.

Review and install a verified CLI version yourself before enabling automatic setup, including any bundled skills it installs. JustCall requests pass through OOMOL, which the skill says manages provider credentials server-side. Keep approval requirements for contact changes, deletions, and suppression-list changes. This review found a setup-control concern, not evidence of 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 (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied chunk performs no visible JustCall operation; its sole action is downloading and executing an external installer. Although installing a required CLI could be a supporting implementation detail, nothing supplied establishes that this installer supports JustCall. The remote script's contents and any further effects cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a live HTTPS response directly into Bash executes whatever the installation endpoint supplies with the invoking user's privileges, without version pinning or independent integrity verification. A compromised distribution endpoint could execute arbitrary code and access local data; the PowerShell alternative has the same underlying risk, although there is no evidence that either endpoint is currently malicious.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

The setup workflow executes remotely downloaded installation scripts without warning the user about local system changes or remote-code execution.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The fallback directs installation through remotely supplied shell or PowerShell code without requiring explicit approval for local code execution and system changes. A missing CLI can therefore turn a JustCall task into an unreviewed software installation; the conditional trigger reduces exposure but does not establish user 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 83)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