Back to skill

Security audit

Chatwork

Security checks for vulnerabilities and agentic risk

Overview

Chatwork actions require approval, but setup can run unverified remote code and introduce broader agent changes that the skill does not explain.

Review setup before enabling this skill. Install a verified CLI release yourself and review or disable automatic skill synchronization using the publisher's controls. Connecting Chatwork lets OOMOL handle its credentials and requests; retain the required approvals for posting, editing, and deleting. The complete bundled skill was inspected, but the external installers and runtime 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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
91% confidence
Finding

The only visible behavior is remote installer execution from an Oomol domain, rather than interaction with Chatwork. Dependency installation can be a supporting implementation detail, but the supplied chunk does not establish that this installer supports the declared purpose. The downloaded script is not supplied, so its further behavior cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The fallback installation command downloads a mutable remote script and immediately executes it with the agent process's local privileges, without version pinning or integrity verification. Compromise of the distribution endpoint could therefore result in arbitrary local code execution; HTTPS and the legitimate dependency relationship do not eliminate that supply-chain risk. The missing-CLI condition limits exposure, but the PowerShell installation example uses the same unsafe execution pattern.

Content

Scanner excerpt · SKILL.md (reported line 69)May include surrounding context.

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 90)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