Back to skill

Security audit

Ai Brain Learning Memory Pro

Security checks for vulnerabilities and agentic risk

Overview

The skill itself is mostly a local Chinese-language memory-methodology guide, but its install instructions use an unpinned global installer that can change the user's agent skill environment.

Review the install path before using this skill. Prefer a pinned commit or manually copy only `ai-brain-learning-memory-pro` into a local skill directory, and avoid the unpinned global `npx ... -g` command unless you trust the current installer and repository contents.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:154
Finding
Unpinned Third-Party Package Execution in Installation Instructions## Vulnerability Details **File Location**: `SKILL.md`, line 154 **Vulnerability Type**: Supply-chain exposure through an unpinned executable dependency **Risk Level**: Medium ### Vulnerable Code ```bash npx skills add zhaoxinghua09-cell/agent-skills -g ``` ### Technical Analysis The documented installation command invokes `npx` without specifying an exact version or integrity digest for the `skills` package. Depending on the local environment, `npx` can retrieve the current package version from the configured package registry and execute its package code. Because the package reference is mutable, the code executed when a user follows these instructions may differ from the code available when this skill was audited. A compromised registry account, malicious package update, dependency compromise, or registry-configuration attack could therefore introduce attacker-controlled behavior. The `-g` option also requests installation into a global skill environment. Although this does not itself elevate operating-system privileges, it increases the persistence and scope of any malicious or unexpectedly modified skill content installed by the command. ### Attack Path 1. An attacker compromises the publisher account, package, transitive dependency, or registry source used to resolve the unpinned `skills` package. 2. The attacker publishes a malicious package version or causes dependency resolution to return attacker-controlled code. 3. A user follows the installation command in `SKILL.md`. 4. `npx` retrieves and executes the mutable package using the invoking user's permissions. 5. The malicious package can access resources available to that user and can install modified skill content into the global skill environment. 6. The installed content may subsequently affect other agent sessions that load or execute those globally installed skills. ### Impact Assessment Successful exploitation permits code execution with the privileges of the user running the document ...[truncated 455 chars]
Remediation
## Remediation Suggestions 1. Pin the installer to a reviewed, immutable version instead of relying on the latest registry release: ```bash npx skills@<audited-version> add zhaoxinghua09-cell/agent-skills ``` 2. Publish and verify a cryptographic integrity digest or signed release artifact before execution. 3. Document the expected package publisher, registry, version, and verification procedure. 4. Avoid global installation by default. Use a project-local or otherwise isolated skill directory unless global availability is explicitly required. 5. Review and lock transitive dependencies through a lockfile or equivalent reproducible dependency mechanism. 6. Prefer installation from a versioned release archive or commit digest whose contents match the audited package. 7. Recommend running installation with least privilege and never through `sudo` or an administrator account.
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (7)

Rp1

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding
The installation instruction uses `npx skills add ...` without pinning a specific package version. `npx` may resolve and execute the latest published package at runtime, which creates a supply-chain risk: a compromised or maliciously updated package could run arbitrary code on the user's machine during installation. In this skill context, the command is presented as a convenient setup path, making accidental execution by users more likely.

Natural-Language Policy Violations

Medium
Confidence
80% confidence
Finding
The category value is written as "AI学习方法论", which indicates a Chinese-language localization choice in the skill metadata. In this manifest there is no accompanying explanation that the skill is region-specific, nor any indication that users can choose or opt into that locale.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The JSON values in the method and dimension fields are entirely in Chinese, indicating a fixed locale for the skill's audit output. There is no accompanying natural-language indication that users may choose another language or that the Chinese-only constraint is required for a region-specific purpose.

Natural-Language Policy Violations

Low
Confidence
81% confidence
Finding
This file contains important descriptive and policy-facing content primarily in Chinese, including originality, dependency, and safety self-check statements. Because the document does not offer an explicit language/locale choice or explain why a Chinese-only presentation is required, it may violate the language/locale policy criterion.

Natural-Language Policy Violations

Low
Confidence
93% confidence
Finding
This markdown file is entirely written in Chinese and does not indicate any optional language selection or opt-in. Under the stated policy, forcing a specific language or locale without user choice is a natural-language policy violation unless the locale constraint is clearly documented and justified.

Natural-Language Policy Violations

Low
Confidence
84% confidence
Finding
This code file contains natural-language strings that define the skill’s purpose and usage entirely in Chinese, with no alternative language option or indication that the skill is intended only for a Chinese-speaking context. Under the policy rule, forcing a specific language without opt-in is a natural-language policy concern.

Natural-Language Policy Violations

Low
Confidence
87% confidence
Finding
The visible text labels in this SVG are entirely in Chinese, including the title, metrics, axis labels, and legend. For a general-purpose skill asset, this imposes a specific language/locale without any indicated user opt-in or documented regional scope.

Static analysis

No suspicious patterns detected.