Back to skill

Security audit

Outline

Security checks for vulnerabilities and agentic risk

Overview

The Outline actions are read-only, but setup directs the agent to execute a downloaded installer without clear approval or integrity checks.

Review and install a verified CLI release yourself before enabling this skill's setup path. Check its bundled-skill installation defaults and the Outline permissions granted through OOMOL. The remote installers and hosted runtime were not verified; the inspected artifact does not establish malicious behavior.

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 command executes an external installer, with no demonstrated connection to Outline or its search/read functionality. This is an undeclared capability, not an established supporting implementation detail. The downloaded script is not supplied, so its exact effects cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a mutable remote script directly into Bash executes it without prior inspection or verification against a trusted release; the PowerShell example has the same weakness. A compromised distribution endpoint or malicious installer could execute arbitrary code with the invoking process's privileges, although the conditional setup path and legitimate CLI dependency reduce exposure and do not establish malicious intent.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

First-time setup executes remotely downloaded installation scripts without warning about their system-level effects.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The missing-CLI fallback directs installation without explaining that downloaded code will run locally or requiring explicit approval for environment changes. Installation is a plausible prerequisite, but a request to read Outline data does not itself authorize executing an installer with the agent's local privileges.

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 81)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