Back to skill

Security audit

Skyfire

Security checks for vulnerabilities and agentic risk

Overview

The Skyfire workflow has clear safeguards, but its fallback setup runs remote installation code without separate approval or adequate disclosure of local changes.

Review and install a verified, pinned CLI release yourself before enabling this skill, and check or disable its automatic skill synchronization. Connecting Skyfire authorizes OOMOL to use that account. Confirm the seller, funding, and identity details before creating a buyer token. The remote installers and server-side implementation could not be verified in this review.

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
99% confidence
Finding

The supplied command installs or runs software from an unrelated domain, with no demonstrated connection to Skyfire data operations. This is an undeclared capability and materially differs from the stated purpose. The contents and further effects of the remote script are not visible in the supplied code.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
83% confidence
Finding

Authentication could support a Skyfire integration, but the supplied chunk contains only a generic login command and establishes no connection to Skyfire. On the supplied evidence, its primary 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

The command pipes mutable remote content directly into Bash without version pinning or independent integrity verification; the PowerShell alternative has the same issue. Compromise of the installer hosting or release pipeline could execute arbitrary code with the agent's local user privileges, exposing accessible files and credentials even though Skyfire tokens are managed server-side.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

Fallback setup executes remotely downloaded installation scripts without warning the user about system changes.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

A missing CLI triggers instructions to execute a remote installer without first obtaining approval for local installation or explaining its system changes. This extends a Skyfire task into local software installation; the missing-command condition limits exposure but does not establish user consent.

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 79)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