Back to skill

Security audit

Exam Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese K-9 exam generator with expected web-search and document-output behavior, but users should be mindful that search queries and generated files may involve educational content.

Install only if you want a China-focused exam-generation helper. Review or confirm web searches before using private student details, unpublished questions, or sensitive school materials, and choose output directories deliberately when saving Word files.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The description explicitly targets Chinese primary/middle school exam generation and frames usage around Chinese curriculum standards, which imposes a specific locale and educational context. Although the skill may be region-specific, the file does not clearly document this as a justified locale constraint or present it as an explicit user choice.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad, common requests such as '生成一份试卷' and 'Create an exam', which increases the chance the skill is invoked when the user did not intend to use this particular capability. Because the skill also claims web-backed validation and file generation, unintended invocation could lead to unnecessary data exposure to search tools or unexpected file writes.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill claims it will automatically use web search to retrieve curriculum standards, standard answers, and perform cross-validation, but the included implementation does not do any of that. This mismatch can mislead users and downstream agents into trusting unverified exam content as externally validated, which is a security-relevant integrity issue because it causes false assumptions about external data access and verification guarantees.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill instructs the agent to automatically use web search for knowledge retrieval and answer validation, but it does not clearly warn users in the description or trigger flow that their request content may be sent to external search systems. This creates a transparency and privacy risk, especially if teachers include unpublished questions, student context, or sensitive educational materials in prompts.

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.txt (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 SOFTWARE OR THE USE OR OTHER

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The save() method is described as only saving exam and answer files in Word format, but it also creates directories and writes multiple files to disk as a side effect. Hidden file-system side effects can surprise callers and, if combined with untrusted output paths, can result in unintended file creation or overwriting in the agent environment.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.