Back to skill

Security audit

Manus

Security checks for vulnerabilities and agentic risk

Overview

The Manus integration has clear approval rules, but its setup can execute a changing remote installer without separate user approval.

Review the automatic installation fallback before installing. Prefer a separately reviewed, version-pinned CLI installation and require approval for local setup changes. Connecting Manus entrusts OOMOL with account access. The bundled instructions show no malicious behavior, but the remote installers and their effects could not be 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
97% confidence
Finding

The supplied code performs remote installer execution rather than Manus data operations. Although installation can be a supporting implementation detail, this chunk provides no evidence that the Oomol installer supports the declared Manus functionality. The downloaded script's contents and further effects are not available for assessment.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a remotely fetched installer directly into bash executes its contents without prior inspection or a pinned, independently verified artifact. HTTPS protects transport but does not protect against a compromised publisher or distribution endpoint, which could deliver code capable of accessing local files and credentials; the missing-CLI condition limits when this risk arises but does not remove it.

Content

Scanner excerpt · SKILL.md (reported line 71)May include surrounding context.

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

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The missing-CLI fallback instructs the agent to execute downloaded shell or PowerShell code without a separate installation approval, integrity verification, or explanation of local system changes. Although conditional and relevant to setup, this expands a Manus data-operation request into local code execution; compromised installer delivery could run arbitrary 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 92)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