Back to skill

Security audit

Control D

Security checks for vulnerabilities and agentic risk

Overview

Control D operations have clear safeguards, but setup directs remote software execution without a separate approval step or clear limits on local changes.

Review setup before enabling this skill. Install a verified, pinned CLI release yourself and review its automatic skill synchronization. Connect only the needed Control D permissions and retain explicit approval for DNS changes. Remote installer and server-side connector behavior remain unverified.

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
99% confidence
Finding

The supplied command performs remote installer execution, not Control D data management. Nothing in the provided chunk establishes that this installer supports the declared purpose, so it cannot be treated as a demonstrated supporting implementation detail. The downloaded script's contents and any further effects are not visible.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an unpinned HTTPS response directly into Bash executes whatever the installer endpoint returns with the invoking user's privileges, without an independent integrity check. A compromised distribution endpoint could therefore execute malicious code; conditional first-time use reduces exposure frequency but does not constrain the script's capabilities.

Content

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

The setup workflow executes downloaded installation scripts without warning about running remote code or modifying the local system.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The missing-CLI fallback directs execution of downloaded installation scripts without requiring explicit approval for local software installation or explaining that arbitrary remote code will run. Although this is relevant first-time setup, the destructive-action confirmation rules concern Control D changes and do not clearly protect local system modifications.

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