Back to skill

Security audit

trip-packer

Security checks for vulnerabilities and agentic risk

Overview

The skill’s travel-map purpose is coherent, but it tells agents to run an unpinned npm CLI through npx, which can execute changing external code during normal use.

Review this skill before installing in sensitive environments. Its outputs and file writes are aligned with making itinerary maps, but the current instructions should be changed to use a reviewed, pinned, lockfile-managed `trip-packer` installation instead of unpinned `npx trip-packer` commands.

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
`; explain and correct each error before building. 5. **Correctly invoke the CLI to build**: - Single city: `npx trip-packer build -d xxx.json -o xxx-map.html` - Multiple cities: use multiple `-d` arguments and optionally `--default-city` - To generate sharing images, append `--images` ``` The original file expresses these instructions in Chinese, including the following executable commands: ```bash npx trip-packer validate -d <file> npx trip-packer build -d xxx.json -o xxx-map.html ``` `plannin ...[truncated 3224 chars]:25
Finding

Unpinned npm Package Is Downloaded and Executed Through npx

Content
View full analysis
`; explain and correct each error before building. 5. **Correctly invoke the CLI to build**: - Single city: `npx trip-packer build -d xxx.json -o xxx-map.html` - Multiple cities: use multiple `-d` arguments and optionally `--default-city` - To generate sharing images, append `--images` ``` The original file expresses these instructions in Chinese, including the following executable commands: ```bash npx trip-packer validate -d npx trip-packer build -d xxx.json -o xxx-map.html ``` `planning-guide.md:82-91`: ```bash # Validate data npx trip-packer validate -d kyoto.json # Build single-city HTML npx trip-packer build -d kyoto.json -o kyoto-map.html # Build multi-city HTML npx trip-packer build -d kyoto.json -d tokyo.json --default-city kyoto -o japan-trip.html ``` ### Technical Analysis The skill directs the agent to invoke `trip-packer` through `npx` without specifying an exact package version. If the package is not already installed locally, `npx` can retrieve it from the configured npm registry and immediately execute its code. The project does not contain a `package.json`, lockfile, package integrity record, or other mechanism that binds execution to a reviewed artifact. It also does not verify the package publisher, provenance, checksum, or registry source. Therefore, the code executed during validation and building may change after this skill has been audited. This creates a supply-chain trust boundary: the commands appear to perform routine validation and HTML generation, but their effective implementation is controlled by whichever packa ...[truncated 2042 chars]
Remediation
View remediation
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (9)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

文件整体以中文规定技能用途和执行方式,但未说明这是用户可选语言,也未提供语言选择或适用范围说明。若该技能在多语言环境中默认要求中文交互,可能违反不得在未经用户选择的情况下强制特定语言的政策。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

该 markdown 文件列出的触发条件如“想生成旅行地图”“想规划某城市行程”“询问如何把自己的旅行数据变成地图页面”等,覆盖面较广,但未给出明确边界、限定上下文或负面示例。缺少何时不应触发该技能的说明,容易与一般旅行建议、路线咨询等日常请求发生重叠。

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
97% confidence
Finding

The skill instructs use of npx trip-packer without pinning an exact package version, which causes execution of whatever version is currently resolved from the registry or local environment. In an agent context, this creates a supply-chain risk: a malicious or newly compromised package release could be fetched and executed during validation or build, leading to arbitrary code execution on the host.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
97% confidence
Finding

The build command again relies on unpinned npx trip-packer, meaning the agent may execute an unexpected package version when producing user artifacts. Because build is an execution step rather than passive parsing, compromise of the package or dependency confusion can directly result in arbitrary command execution, file access, or tampering with produced HTML.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The guide instructs use of npx trip-packer without pinning an exact package version. npx may fetch and execute the latest published package at runtime, which creates a supply-chain risk if a newer version is compromised, typo-squatted, or introduces malicious postinstall/CLI behavior. In this skill context, the command is presented as a normal workflow step, making it more likely an agent or user would execute it directly.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

This build command again uses npx trip-packer without a pinned version, allowing execution of whatever package version is resolved at the time of invocation. If the upstream package is hijacked or a malicious version is published, the build step could run attacker-controlled code on the host system. Because the skill explicitly guides users through building artifacts, this increases practical exploitability.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The multi-city build example also relies on unpinned npx execution, which exposes the same supply-chain execution risk. Since this pattern appears repeatedly in the skill, it normalizes unsafe package execution and increases the chance that downstream users or agents will run an unreviewed remote package.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The entire schema reference is written in Chinese and all field examples, labels, and guidance assume Chinese-language output, but the document does not indicate that this locale restriction is optional or limited to a region-specific use case. Under the stated 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

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This JSON sample uses Chinese titles, notes, addresses, and transit instructions throughout, which effectively fixes the skill content to a specific language/locale. The stated policy for this audit flags language or locale constraints when they are imposed without user choice or an explicit documented justification.

Content

No source excerpt is available for this finding.