Back to skill

Security audit

ThreatFox

Security checks for vulnerabilities and agentic risk

Overview

The ThreatFox lookup workflow is coherent, but its setup can introduce persistent changes to other agent skills without explaining those effects.

Review the CLI installation and its agent-skill changes before use. Prefer a verified, fixed release, and consider the publisher-documented OO_SKILLS_SYNC_DISABLED=1 setting before invoking oo if you do not want automatic skill synchronization. Send only indicators you are authorized to disclose externally. The sole bundled artifact was fully inspected, but the remote installers and hosted connector implementation 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 (6)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied code performs remote installer execution rather than searching or reading ThreatFox data. Nothing in the chunk establishes that this installation is a supporting dependency for ThreatFox access. The downloaded script's further behavior cannot be determined from the supplied code.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The code's only operation is a CLI login, with no visible connection to ThreatFox. Authentication could support a declared service, but the supplied chunk provides no evidence that this login supports ThreatFox access.

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 executes whatever script the remote endpoint currently serves, without verifying its authenticity beyond HTTPS or checking a pinned artifact. Although this is a plausible dependency-installation workflow rather than evidence of malicious intent, compromise of the installer distribution could expose local files, credentials, and the user's execution environment.

Content

Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.

IOC lookups transmit user-provided indicators to external services without a privacy warning.

Medium
Category
Output Handling
Confidence
89% confidence
Finding

The workflow instructs the agent to execute lookups through OOMOL against ThreatFox and labels read actions safe to run directly. It does not warn that submitted indicators, especially internal domains or URLs containing sensitive parameters, are disclosed to external services even though the operation is read-only.

Content

No source excerpt is available for this finding.

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

Medium
Category
Output Handling
Confidence
97% confidence
Finding

The fallback setup directs immediate execution of downloaded shell or PowerShell scripts without a pinned version, independent integrity verification, or explicit installation approval. A compromised distribution endpoint or maliciously changed installer could execute arbitrary code with the invoking user's privileges; the missing-CLI condition limits 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 76)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