Back to skill

Security audit

IXSPY

Security checks for vulnerabilities and agentic risk

Overview

The IXSPY features fit the stated purpose, but setup can execute unverified installers and enable undisclosed changes to other agent skills.

Review the CLI setup before enabling this skill. Install a verified, fixed release yourself and disable startup skill synchronization with OO_SKILLS_SYNC_DISABLED=1 for its invocations if you want to avoid changes to other agents. IXSPY requests use your connected OOMOL account and may consume credits. The remote installers were unavailable for inspection, so their full behavior remains uncertain; the reviewed artifact does not establish malicious intent.

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
96% confidence
Finding

The supplied chunk executes a remote installation script, while the description only declares IXSPY searching and reading. Although installation could support a larger implementation, no connection between this installer and IXSPY is established in the supplied material. The downloaded script's contents and downstream effects cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
86% confidence
Finding

The supplied code performs only an authentication operation and establishes no connection between oo and IXSPY. Authentication could support an IXSPY integration, but that relationship is not demonstrated here; the visible behavior does not substantiate the declared purpose.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

Piping curl output directly into bash executes mutable remote content without inspecting or independently verifying it. If the installer endpoint or its publishing infrastructure is compromised, this can expose accessible files and credentials or permit persistent local changes; this is the same underlying installation risk as SQP-2, not a separate exploit.

Content

Scanner excerpt · SKILL.md (reported line 75)May include surrounding context.

Fallback setup executes remotely downloaded installation scripts without a safety warning.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

The fallback directs execution of remotely retrieved shell or PowerShell scripts without version pinning, independent integrity verification, or explicit installation approval. Although conditional setup and a vendor-associated HTTPS domain reduce suspicion, a compromised distribution endpoint could execute arbitrary code with the agent process'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 96)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