Back to skill

Security audit

HTML/CSS to Image

Security checks for vulnerabilities and agentic risk

Overview

Review is needed because setup executes unverified downloaded scripts and omits the CLI’s documented changes to other agent skills.

Use a reviewed, pinned CLI installation before enabling this skill. Disable startup skill synchronization with OO_SKILLS_SYNC_DISABLED=1 if you do not want broader agent changes. Consider whether submitted HTML/CSS is suitable for processing through OOMOL, and retain the required approval steps for image creation and deletion. The remote installers and CLI binary were not audited.

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
99% confidence
Finding

The supplied command performs remote script execution rather than HTML/CSS to Image operations. Nothing in the supplied chunk establishes that installing the Oomol CLI is a supporting requirement for the declared service. The downloaded script's contents and any subsequent 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

The curl-to-Bash command immediately executes whatever script the remote endpoint returns, without version pinning or independent integrity verification. HTTPS protects transport but does not prevent a compromised publisher or hosting endpoint from supplying malicious code; this overlaps the setup vulnerability identified by SQP-2 rather than representing a separate attack path.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

Setup instructs immediate execution of downloaded installation scripts without a system-integrity warning.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The setup instructions pipe downloaded scripts directly into Bash or PowerShell without verifying their integrity or obtaining explicit installation approval. If the installer endpoint or delivery infrastructure is compromised, this can execute attacker-controlled code with the invoking user's permissions; restricting setup to a missing-CLI error reduces exposure but does not remove that risk.

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 80)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