ClawHub
Back to skill

Security audit

jackyshen-gen-quotation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward quotation/proposal PDF generator that writes expected document files locally, with no evidence of hidden exfiltration, destructive behavior, or unrelated privilege use.

Install this if you want a local quotation/proposal PDF generator. Be aware that generated documents and intermediate files can remain in the workspace output directory and may include customer names, pricing, payment terms, and bank account information, so use it in an appropriate workspace and clean up outputs when needed.

SkillSpector

Vulnerability Patterns
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill instructs the agent to generate intermediate and final files under ./output and to invoke a Python rendering workflow, but it does not declare permissions corresponding to file creation/writes. This creates a transparency and policy gap: users and the platform may not realize the skill will persist data to disk, which can lead to unintended storage of potentially sensitive quotation, pricing, and customer information.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The documented trigger phrases are very broad, such as asking to generate a quotation or proposal, and can easily match ordinary conversation that is not intended to invoke this skill. In an agent environment, this can cause unintended activation, leading the system to collect business details or generate documents when the user did not explicitly request this capability.

Vague Triggers

Medium
Confidence
82% confidence
Finding
The trigger description is broad enough to match common business conversation terms such as '报价', '提案', '商业文档', or mentions of pricing and consulting fees. Over-broad activation can cause the skill to run in contexts where the user did not intend document generation, increasing the chance of collecting sensitive business data or writing files unexpectedly.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly requires creating rendered template files and final output files in the current working directory's ./output folder, but it does not clearly warn the user at runtime that local files will be created. This can surprise users, leave sensitive commercial information on disk, and increase exposure if the workspace is shared or later inspected by other processes.

Static analysis

No suspicious patterns detected.