ClawHub
Back to skill

Security audit

Braze

Security checks for vulnerabilities and agentic risk

Overview

The Braze features match the description, but setup directs the agent to execute an unchecked online installer without a clear approval step.

Review and install a verified CLI release yourself before allowing agent use, and check its automatic skill synchronization settings. Use a read-scoped Braze connection and understand that requests pass through OOMOL. The remote installer and live connector implementation were not inspected; no malicious payload was established.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied code executes a third-party installer and contains no visible Braze interaction. There is no evidence that this installation is a supporting implementation detail required for the declared Braze functionality. The remote script's contents and any further effects cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The setup instructions pipe a remotely fetched, unpinned script directly into Bash; the Windows alternative similarly executes downloaded content immediately. Compromise of the installer distribution path could therefore execute arbitrary code with the invoking user's privileges, exposing local files and credentials. The missing-CLI prerequisite limits exposure, and a strictly enforced Bash(oo *) restriction may block the installer, but neither makes this installation guidance safe.

Content

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

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