ClawHub
Back to skill

Security audit

pdf-studio

Security checks for vulnerabilities and agentic risk

Overview

This PDF-generation skill is purpose-aligned and local-only, with minor trigger and language-template clarity issues but no evidence of hidden or unsafe behavior.

This skill is reasonable to install if you want local PDF-generation guidance. Review any generated code before running it, install PDF libraries yourself from trusted sources, and be aware that some prompts and templates are Chinese-focused despite broader multilingual claims.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The feature list states support for multiple languages including Japanese, but the requirements template later limits the language field to only 中文/英文. This creates a natural-language locale restriction without user opt-in and conflicts with the broader multilingual claim.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger phrases are broad enough to match many ordinary user requests such as creating reports, invoices, or certificates, which can cause the skill to activate unexpectedly. In a tool that may generate and suggest code or file-processing steps, overbroad activation increases the chance of unintended execution paths, misuse of local files, or user confusion about which capability is being invoked.

Scope Creep

Low
Category
Excessive Agency
Content
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
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.

Natural-Language Policy Violations

Low
Confidence
84% confidence
Finding
This markdown file presents template names in both English and Chinese, but the actual template section items are written only in Chinese. That can impose a specific language/locale on users without explicit opt-in or an alternative, which matches the policy concern for language-choice handling.

Static analysis

No suspicious patterns detected.