Back to skill

Security audit

qubrics-token-efficient-usage

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with medium confidence: the scans found no AIG issues, but Skillspector reported possible undeclared agent setup and owner-management actions, so the evidence is incomplete and purpose alignment is uncertain.

The verdict is benign, but medium confidence and partial Skillspector coverage mean the review is not complete. Before installing, consider whether agent setup, mailbox access, and owner invitations fit your intended use; the scans leave that purpose match uncertain.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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 (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The commands perform agent onboarding, mailbox access, and ownership administration rather than selecting or optimizing low-token Qubrics calls. These capabilities are not disclosed by the declared purpose, and the supplied chunk does not demonstrate the stated optimization techniques.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 13)May include surrounding context.

md
envVars:
      - name: "QUBRICS_ACCESS_TOKEN"
        required: false
        description: "Optional externally managed OAuth access token for CLI HTTP requests; the CLI does not refresh it."
      - name: "QUBRICS_API_KEY"
        required: false
        description: "Optional Qubrics API key or scoped agent token used by CLI, SDK, HTTP, or MCP examples."

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 25)May include surrounding context.

md
description: "Optional Qubrics CLI profile name."
      - name: "SENDMUX_ACCESS_TOKEN"
        required: false
        description: "Optional externally managed OAuth access token for CLI HTTP requests; the CLI does not refresh it."
      - name: "SENDMUX_API_KEY"
        required: false
        description: "Optional Qubrics API key or scoped agent token used by CLI, SDK, HTTP, or MCP examples."

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 41)May include surrounding context.

md
## ClawHub account note

This ClawHub skill connects OpenClaw agents to Qubrics. Some workflows require a Qubrics account and an appropriate Qubrics API key or agent token. Qubrics account usage is external to ClawHub; do not ask users to paste secrets into chat.

Use this skill to choose the lowest-cost Qubrics route that still answers the task correctly.

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 51)May include surrounding context.

md
For the documented keyless self-registration flow, complete registration first, then verify the newly saved profile before content reads, sending or other task work. For existing credentials or profiles, verify the returned connection identity and any authorised mailbox selection against the intended account and credential before task work. A permission grant alone does not establish the intended identity. If identity differs or cannot be verified, stop and resolve it with the user rather than reading or mutating another account.

- Do not ask the user to paste an API key.
- For API-key authentication, use `smx_mbx_*` keys for normal Mailbox calls.
- For a self-registered agent, reuse one durable CLI profile. Mailbox reads become available after provisioning, before owner approval; Sending stays blocked until owner approval.
- For API-key authentication, use `smx_root_*` for Management calls.