Back to skill

Security audit

CloudConvert

Security checks for vulnerabilities and agentic risk

Overview

Review recommended because setup can run downloaded installation code without asking, although CloudConvert changes require approval.

Review and approve CLI installation separately, using a pinned and verified release. Consider whether additional agent skills should be synchronized; the documented OO_SKILLS_SYNC_DISABLED setting disables that behavior. OOMOL mediates the connected account's operations. CloudConvert writes and deletions have explicit approval safeguards, and no malicious behavior was established in the bundled 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 chunk performs remote installer execution rather than CloudConvert operations. Nothing in the chunk establishes that this installer is a supporting dependency for CloudConvert. The downloaded script's contents and 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 HTTPS response directly into bash executes mutable remote content without version pinning or independent integrity verification. Compromise of the installer host or publishing pipeline could therefore execute attacker-controlled code with the user's permissions; the legitimate OOMOL dependency explains the destination but does not remove this supply-chain risk.

Content

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

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

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The fallback directs the agent to execute a remote installer without explicit approval for local code execution or installation changes. Although this is a legitimate dependency setup step and only occurs when the CLI is missing, it expands a CloudConvert request into execution of externally supplied code with the invoking user's permissions.

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