ClawHub
Back to skill

Security audit

Markdown Studio

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Markdown document generator with disclosed file output and image embedding behavior, but users should be mindful when embedding local images as base64.

Install only if you want an agent to help create Markdown files. When using image embedding, provide only images you are comfortable including directly in the generated Markdown, because base64 embedding copies the image data into the document.

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
  • 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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill explicitly supports reading local image files and embedding their contents as base64 into generated Markdown, but it does not present a prominent user-facing warning or consent step about local file access and data inclusion. This creates a real risk of unintentionally exfiltrating sensitive local files into documents, especially because embedded base64 hides the fact that raw file contents are being copied into output.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases are broad enough to activate on many ordinary writing requests such as creating reports, technical documentation, or wiki pages, which increases the chance the skill is invoked outside a narrowly intended context. Overbroad activation is dangerous because it can cause unintended tool use and expand the skill's opportunity to access local resources or generate files when the user only asked for generic assistance.

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

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

This markdown file includes category labels in Chinese alongside English, such as '技术文档', '商务文档', '学术文档', and '个人文档'. Because the file presents a specific bilingual/localized format without stating that language choice is optional or context-specific, it may conflict with a policy requiring user opt-in for language or locale selection.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.