Back to skill

Security audit

AroFlo

Security checks for vulnerabilities and agentic risk

Overview

The AroFlo workflow fits its purpose, but missing the required CLI triggers downloaded code execution without a separate installation approval step.

Review and approve the CLI installation separately before allowing fallback setup. Prefer a verified, fixed release and check whether it installs additional agent skills. Connecting AroFlo entrusts its credentials and requested business data to OOMOL. The downloaded installer and hosted connector implementation were not verified; no malicious behavior was established.

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 code installs software from an Oomol endpoint; it does not visibly search or read AroFlo data. No connection establishes this installer as a supporting requirement for AroFlo access. The downloaded script's contents are not supplied, so its further 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 HTTPS response directly into Bash executes remote code without a pinned version or independently verified integrity; the PowerShell alternative has the same weakness. Compromise of the distribution endpoint or release pipeline could result in arbitrary code execution with the user's privileges, including theft of accessible credentials and files, despite the AroFlo actions themselves being read-only.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

The setup workflow executes downloaded installation scripts without warning the user about the system-integrity implications.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The fallback directs an agent to execute downloaded installation scripts without explaining that this runs third-party code with the invoking user's privileges or requesting installation-specific approval. Restricting this to a missing CLI reduces exposure, but an AroFlo read request should not implicitly authorize system changes.

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 82)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