Back to skill

Security audit

红果短剧口碑复盘

Security checks for vulnerabilities and agentic risk

Overview

The skill is rated suspicious because it repeatedly runs an unpinned latest release of a CLI, creating a supply-chain risk around credentials and the invoking account.

Consider installing only after the CLI package is pinned to a reviewed version and its installation is verified. The scan is partial: some local references could not be resolved, so the available evidence is incomplete; the verdict is suspicious, not a claim of malicious intent.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (10)

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 27)May include surrounding context.

md
` 与来源 `environment` / `file` / `null`,不输出 Key。安装或升级时,已有凭证可读、没有已知鉴权失败且用户未明确要求更换 Key,就复用原来源继续原任务,不重新登录、不迁移或改写已有凭证;命令、权限或文件格式错误按实际错误处理,不一律判为没配置。已认证的 hosted MCP 沿用当前连接鉴权,不要求另配本地 CLI。
- 仅首次配置、凭证缺失或失效,或用户明确要求更换 Key 时才录入:用户已在安装提示词或当前对话中提供 Key 并授权配置时,用 `npx -y socialdatax-skills@latest auth login --stdin` 接收这枚 Key 的标准输入,由 CLI 长期保存;不要求用户重复手动录入,不把 Key 作为 CLI 参数或写入临时脚本文件。没有提供 Key 时,引导用户从上述官网获取,在本地终端运行 `npx -y socialdatax-skills@latest auth login`,按隐藏输入提示填写,不主动要求其发到对话。Key 保存到当前执行用户主目录的 `.config/socialdatax/credentials.json`;Unix 权限 600,Windows 当前用户私有 ACL。不要在回复、输出日志、截图、命令示例、Skill 或版本库再次展示 Key;Agent 不读取或展示凭证文件内容。
- CLI 每次调用都会读取该私有用户文件,不依赖客户端加载 Shell 配置,不需要改客户端或系统设置。非空 `SOCIALDATAX_API_KEY` 优先,既有旧兼容变量其次,最后读取文件;`source=environment` 时保存文件不会覆盖生效的环境凭证;保存成功不等于本次所选 Key 已生效。CLI 提示不同 Key 冲突时,先说明实际来源,不擅自删除或改写既有环境配置。鉴权失败先核对实际来源和账号,再由用户本地修正,保留其它配置。
- 完成保存后,在实际业务命令的同一执行环境重新运行 `auth status`。false 时停止业务调用,核对操作系统用户、主目录与文件访问权限;true 只说明凭证可读,鉴权与结果仍以原业务请求返回为准,不为配置检查额外调用收费接口。
- 远程或容器中的 CLI 读取远程或容器用户的配置,本机保存不会自动传入。具备持久主目

MCP server referenced without pinned version: 'npx -y socialdatax-skills'.

Medium
Category
MCP Rug Pull
Confidence
99% confidence
Finding

The auth-status command executes socialdatax-skills@latest through npx with automatic approval, rather than a reviewed, fixed version. A compromised release could execute with the agent's permissions and access available credentials even though this command is described as only checking authentication status; this is a CLI supply-chain risk, not specifically an MCP-server issue.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx -y socialdatax-skills'.

Medium
Category
MCP Rug Pull
Confidence
99% confidence
Finding

The interactive login example also executes socialdatax-skills@latest without a fixed version. Hidden input protects against casual display of the API key, but it cannot protect the key from a malicious version of the program receiving it.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx -y socialdatax-skills'.

Medium
Category
MCP Rug Pull
Confidence
99% confidence
Finding

The stdin-based login command runs a mutable @latest package while supplying an API key directly to it. Although stdin avoids exposing the key in command-line arguments, a compromised package release could capture that key and execute arbitrary code with the agent's permissions.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx -y socialdatax-skills'.

Medium
Category
MCP Rug Pull
Confidence
99% confidence
Finding

The series-detail example uses npx -y with @latest, allowing a changed package release to execute without version review. The intended read-only API operation does not restrict the local program's filesystem, credential, or network access.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx -y socialdatax-skills'.

Medium
Category
MCP Rug Pull
Confidence
99% confidence
Finding

The comments command resolves a mutable @latest release and automatically approves its execution. A compromised release could steal the configured service key or other accessible data; limits on returned comments do not constrain executable behavior.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx -y socialdatax-skills'.

Medium
Category
MCP Rug Pull
Confidence
99% confidence
Finding

The search example executes an unpinned @latest package using npx -y. This creates the same supply-chain exposure as the other commands: compromise of a subsequently resolved release could yield code execution with access to the agent's environment and service credentials.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx -y socialdatax-skills'.

Medium
Category
MCP Rug Pull
Confidence
99% confidence
Finding

The series-ID detail command executes socialdatax-skills@latest rather than a fixed, reviewed release. Using an ID instead of a URL does not mitigate package compromise, which could expose credentials or permit arbitrary actions under the invoking account.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx -y socialdatax-skills'.

Medium
Category
MCP Rug Pull
Confidence
99% confidence
Finding

The series-ID comments example automatically executes a floating @latest package. The skill's read-only workflow and sample-size limits do not sandbox the executable, so a compromised release could access secrets and local files.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx -y socialdatax-skills'.

Medium
Category
MCP Rug Pull
Confidence
99% confidence
Finding

The replies example also relies on npx -y socialdatax-skills@latest, making executable selection dependent on a mutable registry tag. A malicious release could run with the agent's permissions and retrieve the API key, regardless of the narrow reply-query purpose.

Content

No source excerpt is available for this finding.