Back to skill

Security audit

brain-design-benchmark

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only benchmarking framework with no executable code, persistence, credential use, or hidden authority.

Install only if you are comfortable using a mostly Chinese research/evaluation framework. It appears safe from an execution and permissions standpoint, but its evidence section is marked TBD, so treat its benchmark scores and claims as a starting framework rather than independently validated research.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The file presents all operational guidance in Chinese, including the title and agent instructions, but does not indicate that language use is optional or limited to a justified region-specific context. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Line L03 presents the skill behavior entirely in Chinese and gives mandatory-style instructions, but the README does not indicate that language choice is optional or configurable. This creates a natural-language locale policy issue because it implicitly enforces a specific language without user opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The primary skill description is written entirely in Chinese and provides the operational instruction in that language, with no indication that users may choose another language or that the skill is limited to a Chinese-speaking context. This can violate language/locale policy because it implicitly imposes a specific language without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The changelog states a 'Bilingual rewrite (full EN+ZH, English first)' and the document is structured to present English before Chinese. This imposes a language/locale preference in the skill's natural-language instructions without offering the user a choice or documenting that the skill is region-specific.

Content

No source excerpt is available for this finding.