ClawHub
Back to skill

Security audit

字帖生成器与练字助手｜字帖库

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese handwriting worksheet helper that uses a local Python script to build printable worksheet links, with its privacy limits and website handoff disclosed.

Before installing, be aware that the skill can run its bundled Python script and create links containing the worksheet text in compressed but reversible form. Do not put sensitive child details such as full class, student ID, or private links into public places, and preview the worksheet on the website before printing.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (6)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
85% confidence
Finding

The skill instructs the agent to read local reference files and run a local Python script, and it also directs users to open an external website for preview and printing, but it does not declare any explicit tool scope such as allowed file paths or network destinations. This creates an authorization boundary problem: a host agent may grant broader file-read or network capabilities than the skill actually needs, increasing the chance of overreach or misuse if the skill is invoked in a permissive environment.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The display name, description, and default prompt are entirely in Chinese and do not indicate that users may choose another language. This can violate a language/locale policy when a skill implicitly requires a specific language without opt-in or documented justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest’s default prompt describes invocation in broad conversational terms like '帮我安排一次合适的练字练习并生成 A4 打印字帖' ('help me arrange a suitable handwriting practice and generate an A4 worksheet'). In a manifest file, this lacks explicit trigger boundaries or exclusion conditions, which could overlap with ordinary user requests about handwriting practice rather than a clearly scoped skill invocation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

This JSON manifest contains user-facing natural-language strings entirely in Chinese, beginning with preset names and descriptions at L0057-L0058 and continuing throughout the file. Under the locale policy rule, forcing a specific language without an explicit user choice or documented region-specific constraint is a policy concern for all file types.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code file contains natural-language descriptions, CLI help text, and error messages exclusively in Chinese. The skill does not indicate that it is region-specific or provide a user language choice, which can violate language/locale policy requirements for skills expected to adapt to user preference.

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