Back to skill

Security audit

采访问题与追问清单

Security checks for vulnerabilities and agentic risk

Overview

This skill consistently limits itself to drafting Chinese interview outlines from supplied materials, with ordinary installation precautions.

Expect Chinese outlines and provide public excerpts, a topic, and a duration. If using the README installer, review the CLI version and repository revision because the command does not pin them. Verify source facts and publication permissions before using the resulting outline.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (10)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The provided chunk performs skill installation, not the declared interview-planning task. External skill retrieval and installation are not described capabilities. Although this README command may be setup documentation for a skill whose implementation was not supplied, the available chunk does not establish that the installed skill fulfills the declared purpose. This assessment does not imply that the external skill is malicious.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The installation command invokes an unpinned npm CLI through npx and references a skill repository without an immutable revision, creating a supply-chain reproducibility risk. If either upstream is compromised or changed maliciously, a user following the instructions could execute untrusted code or install altered skill instructions. The finding incorrectly labels this an MCP server reference; the actual concern is the mutable installation dependencies, not MCP.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
85% confidence
Finding

The installation example uses an unpinned npx skills command, which can download and execute a changing npm package with the invoking user's permissions. A compromised future release could therefore execute malicious code, although the README provides no evidence of an actual compromise or automatic execution. The finding incorrectly calls this an MCP server reference; the supported concern is dependency supply-chain exposure.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · LICENSE (reported line 12)May include surrounding context.

text
permit persons to whom the Software is furnished to do so.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE

The skill specifies Chinese output without user language opt-in.

Low
Category
Output Handling
Confidence
91% confidence
Finding

The description specifies a Chinese interview outline regardless of the user's language. It neither offers a language choice nor explains a locale-specific requirement that justifies this restriction.

Content

No source excerpt is available for this finding.

The skill specifies Chinese-language interview outlines without offering a language choice or opt-in.

Low
Category
Output Handling
Confidence
91% confidence
Finding

Line L05 explicitly defines the output as a Chinese interview outline (“中文采访提纲”). The README does not offer a language choice or explain a regional requirement that justifies fixing the output language.

Content

No source excerpt is available for this finding.

The description requires Chinese-language output without offering a language choice or opt-in.

Low
Category
Output Handling
Confidence
97% confidence
Finding

The phrase “产出一份可直接执行的中文采访提纲” explicitly requires the interview outline to be in Chinese. The file provides neither a user language choice nor a region-specific justification for this restriction; the issue is the explicit output requirement, not that the instructions are written in Chinese.

Content

No source excerpt is available for this finding.

The skill specifies Chinese-language interview questions without offering a language choice or opt-in.

Low
Category
Output Handling
Confidence
92% confidence
Finding

The short description explicitly specifies Chinese interview questions ("中文采访问题"), rather than merely using Chinese to describe the skill. No user language choice, explicit opt-in, or region-specific justification for this output-language constraint is provided.

Content

No source excerpt is available for this finding.

The manifest requires Chinese-language output without an explicit user language choice.

Low
Category
Output Handling
Confidence
93% confidence
Finding

The description specifies generating Chinese interview questions, and line 25 repeats this output-language constraint. Although the skill is labeled as Chinese-oriented, it does not offer a language choice or explain why Chinese output is necessary rather than following the user's preferred language.

Content

No source excerpt is available for this finding.