Back to skill

Security audit

抖音-短链转换 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill performs the advertised Douyin link conversion, but its setup instructions are broad for a simple link tool and can install software, change command paths, and configure external-service credentials.

Review this before installing if you do not want a skill to install Node/npm packages, use unpinned external CLI code, or configure Qinghu API credentials on your machine. If used, prefer a preinstalled, pinned qhkit version and provide only Douyin links you are comfortable sending to Qinghu's service.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (7)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger condition says the skill must activate for 'similar requests' without clear boundaries, which can cause over-broad invocation. In practice, that raises the risk of routing unrelated user content or URLs to this external tool unexpectedly, with privacy and least-privilege concerns.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill does not clearly warn users that submitted Douyin links will be transmitted to a third-party external service (qhkit/青虎数据) for processing. Even if the link seems harmless, it may contain identifiers or private/share-only references, so omission of this disclosure weakens informed consent and privacy expectations.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

For a simple link-conversion skill, the environment self-bootstrapping section is overly broad: it directs installation of Node, global packages, PATH changes, alternate registries, and platform-specific setup. This materially expands the action surface from 'convert a URL' to arbitrary software installation and persistent environment modification, increasing the chance of unintended system changes or dependency abuse.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
89% confidence
Finding

The skill instructs use of npx @iqinghu/qhkit without pinning an exact version, which allows whatever package version is current at execution time to be fetched and run. In a skill context, that creates a supply-chain risk because behavior can change unexpectedly or a compromised upstream release could execute attacker-controlled code.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
92% confidence
Finding

This duplicated finding flags the same persistence behavior: installing Node binaries under the user's home directory and exporting a modified PATH. That expands the skill from data processing into system reconfiguration, which is disproportionately risky for the claimed purpose and can affect subsequent commands outside the current task.

Content

Scanner excerpt · SKILL.md (reported line 80)May include surrounding context.

Linux 二进制安装(装到用户目录,无需 root;先校验官方 SHA256 再解包):

cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | sha256sum -c - mkdir -p "$HOME/.local/lib" && tar -xJf /tmp/node-v22.22.3-linux-x64.tar.xz -C "$HOME/.local/lib" export PATH="$HOME/.local/lib/node-v22.22.3-linux-x64/bin:$PATH"

text

Session Persistence

Medium
Category
Rogue Agent
Confidence
92% confidence
Finding

This duplicated finding flags the same persistence behavior: installing Node binaries under the user's home directory and exporting a modified PATH. That expands the skill from data processing into system reconfiguration, which is disproportionately risky for the claimed purpose and can affect subsequent commands outside the current task.

Content

Scanner excerpt · SKILL.md (reported line 80)May include surrounding context.

Linux 二进制安装(装到用户目录,无需 root;先校验官方 SHA256 再解包):

cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | sha256sum -c - mkdir -p "$HOME/.local/lib" && tar -xJf /tmp/node-v22.22.3-linux-x64.tar.xz -C "$HOME/.local/lib" export PATH="$HOME/.local/lib/node-v22.22.3-linux-x64/bin:$PATH"

text

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill tells the agent/user how to obtain and configure API tokens for an external service, including setting persistent credentials in CLI config or environment variables. That exceeds the justified scope of a link-conversion skill and creates credential-handling risk, including accidental disclosure, misuse of the user's account, and durable secrets left on the host.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.