Back to skill

Security audit

Wrike

Security checks for vulnerabilities and agentic risk

Overview

The Wrike integration is coherent, but its setup can execute unverified remote installers and introduce lasting changes beyond Wrike.

Review and explicitly approve CLI installation before allowing setup. Prefer a verified, fixed release and keep confirmation for Wrike changes. OOMOL will mediate access to your connected account. Review its automatic skill deployment; the [CLI reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables) documents OO_SKILLS_SYNC_DISABLED to disable startup synchronization. The downloaded installers and hosted 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
96% confidence
Finding

The supplied code performs remote installer execution rather than accessing Wrike data. No Wrike integration or connection between the Oomol installer and the declared functionality is shown, so this cannot be established as merely a supporting implementation detail. The downloaded script's further behavior is not visible in the supplied chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command streams a remotely fetched script directly into Bash without pinning a version or verifying its integrity; the PowerShell alternative has the same execution pattern. A compromised distribution endpoint or malicious installer update could execute arbitrary code with the agent process's privileges, potentially accessing local data and credentials. HTTPS and the missing-CLI precondition reduce exposure but do not establish installer integrity.

Content

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

First-time setup executes remotely downloaded installation scripts without warning about system changes or requesting approval.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The fallback directs the agent to install software after a missing-command error without requiring user approval or explaining host-system changes. Although conditional on a missing dependency, this expands authorization for a Wrike task into local software installation; the Wrike write-confirmation rules do not cover this operation.

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