Back to skill

Security audit

Kadoa

Security checks for vulnerabilities and agentic risk

Overview

The Kadoa features fit their stated purpose, but setup can run unverified downloaded code without a separate approval step.

Review setup before installing. Install a verified CLI release yourself and require approval before running any downloaded installer. Upstream documents OO_SKILLS_SYNC_DISABLED for preventing automatic skill synchronization. OOMOL will broker access to your connected Kadoa account, so limit its permissions and protect signed export links. The remote installer and CLI 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 (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied command performs remote software installation rather than searching or reading Kadoa data. Nothing in the supplied chunk establishes the Oomol installer as a supporting dependency for Kadoa functionality. The downloaded script's further behavior is not visible, but fetching and executing it is explicit.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
84% confidence
Finding

The supplied code performs only a login operation and contains no Kadoa search or read behavior. Authentication could be a supporting implementation detail, but the supplied chunk does not establish that oo authenticates to Kadoa or supports the declared functionality.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command pipes a mutable network response directly into Bash without a pinned version or independent integrity verification; the PowerShell alternative uses the same execution pattern. Compromise of the distribution endpoint or installer could execute attacker-controlled code with the invoking user's privileges, potentially exposing local files and credentials; legitimate dependency setup does not remove this supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

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

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The fallback directs the agent to install software by executing downloaded scripts without first explaining the local changes or requesting approval. A missing dependency is a legitimate setup condition, but it does not authorize arbitrary installer side effects; the declared oo-only tool allowance may limit execution if strictly enforced, rather than making these instructions safe.

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 79)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