Back to skill

Security audit

Monica CRM

Security checks for vulnerabilities and agentic risk

Overview

The CRM workflow has clear safeguards, but its setup fallback executes unverified remote code without requiring separate user approval.

Review and explicitly approve CLI installation before allowing the fallback, preferably using a verified fixed release. Check whether automatic installation or synchronization of other agent skills is wanted. OOMOL will mediate access to private CRM data; retain the required confirmations for writes and deletions. The remote installer and hosted connector implementation were not 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
97% confidence
Finding

The supplied chunk performs remote software installation rather than Monica CRM operations. Nothing in the chunk establishes that this installer is a supporting dependency for the declared CRM functionality. The downloaded script's contents are not provided, so its further effects cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a downloaded script directly into Bash executes whatever the installation endpoint returns, without a pinned version or independent integrity verification; the PowerShell alternative has the same issue. A compromised distribution endpoint could execute arbitrary code with the agent process's permissions, potentially exposing accessible files and credentials; HTTPS and conditional installation reduce exposure but do not prevent this supply-chain attack.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

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

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The fallback instructs the agent to install software by executing a remote script without explicitly requiring approval for local code execution and system changes. Confirmation requirements elsewhere cover CRM writes and deletions, not installation, leaving a consent gap even though setup occurs only when the CLI is missing.

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 82)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