Back to skill

Security audit

Woot

Security checks for vulnerabilities and agentic risk

Overview

The Woot features fit their purpose, but setup instructs the agent to execute downloaded installation code without a clear approval step.

Review setup before installing. Verify and install the CLI yourself, require approval for installation changes, and review its automatic skill synchronization. The [publisher's command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md) documents OO_SKILLS_SYNC_DISABLED for disabling startup synchronization. OOMOL mediates Woot requests and credentials. The artifact shows no malicious intent, but downloaded installer code and the hosted backend 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
97% confidence
Finding

The supplied chunk performs remote installer execution rather than searching or reading Woot data. It contains no Woot-specific operations or evidence establishing the installer as a supporting dependency. The remote script's contents are not supplied, so its additional effects cannot be determined.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The supplied code only initiates authentication and shows no connection to Woot or implementation of the declared functionality. Authentication could be a supporting step in a larger implementation, but the supplied chunk provides no evidence of that relationship.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an unpinned HTTPS response directly into Bash executes whatever code the installation endpoint returns, without verifying an immutable artifact or trusted signature. Compromise of the endpoint or its publishing pipeline could lead to local data theft or modification under the user's account; this overlaps with the setup-workflow finding rather than representing a separate attack chain.

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

The setup workflow executes remotely downloaded installation scripts without warning the user about the system-integrity implications.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The fallback setup instructs the agent to execute downloaded shell or PowerShell scripts without an explicit user-approval step or artifact verification. A compromised distribution endpoint could thereby execute arbitrary code with the invoking user's privileges; although conditional setup reduces exposure, it exceeds the system changes normally expected from a Woot read request.

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 78)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