Back to skill

Security audit

小说开篇钩子改稿

Security checks for vulnerabilities and agentic risk

Overview

The skill stays within its stated writing task; its optional installer has ordinary dependency-version risks.

Use an assistant you trust with your manuscript. For installation, prefer copying the reviewed files or pinning the installer and repository revision.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied command performs skill installation; it contains no behavior that rewrites an opening, produces three versions, or explains edits. Although the repository name aligns with the declared topic, its contents are not supplied and cannot establish that the installed skill implements the description. The observable behavior is therefore materially different from the declared purpose.

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 command npx skills add xxjrq/novel-opening-hook-cn can download and execute an unpinned version of the skills package, exposing users to supply-chain compromise or unexpected future releases. This is a CLI installation instruction, not an MCP server reference, so the static finding's category is inaccurate even though the unpinned-execution concern is valid. The command is presented as an optional manual installation step, which limits exposure; nothing in the supplied file demonstrates malicious intent.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The installation command uses npx skills without an exact version, allowing execution of a package version that may change over time. A compromised package release could execute code with the installing user's permissions; however, this is an optional installation instruction, not evidence of malicious behavior or an MCP server reference.

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