Back to skill

Security audit

FoodDocument研发资料整理或文档编写

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward R&D document-management helper that stores document indexes locally and suggests generic web searches, with no evidence of hidden execution or data theft.

Install only if you want a Chinese-language R&D document workflow. Be aware it keeps a local document index under data/docs and may prompt generic web searches for documentation standards; avoid putting confidential project details into web-search queries unless you intend to send them externally.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (11)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill declares capabilities that imply local file reads and writes through its documented storage behavior and referenced scripts, but it does not define any explicit tool scope or permission boundaries. This can cause the agent to access or modify files more broadly than users expect, especially in a workspace containing unrelated sensitive documents.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger conditions are broad enough to match routine document-writing and organization tasks, which increases the chance of automatic or inappropriate activation. In practice, that can cause unintended web searches or persistent storage actions during ordinary work, expanding data exposure beyond the user's intent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs the agent to perform external web searches and to persist documents locally, but it does not disclose either outbound data flow risks or retention behavior. This is dangerous because users may provide proprietary R&D material without realizing that queries could reveal sensitive context externally and that generated or indexed artifacts will remain on disk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The file-level description and all user-facing strings are written exclusively in Chinese, and the CLI does not provide any option for users to select another language. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly justified.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest scopes this skill to document classification, version management, and template generation for organizing R&D documents. The function at L019-L030 adds an external information-retrieval behavior by preparing web searches for document standards, which goes beyond managing local documents and their metadata.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The manifest description and operational instructions are entirely in Chinese, which implies a fixed language/locale for use. There is no statement that the skill supports user language preference or that it is intentionally restricted to a Chinese-speaking or region-specific environment.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file uses Chinese exclusively for the title, headings, and table content, which can amount to forcing a specific language without user opt-in. The file does not indicate that the template set is intended only for a Chinese-speaking or region-specific audience, nor does it offer alternatives.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file is natural-language content, so language-policy checks apply. The template forces a single language/locale for all users, and there is no indication that the skill is intentionally limited to Chinese-speaking or region-specific use.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown template presents all user-facing content in Chinese and does not offer any language choice, opt-in, or explanation that it is intended only for a Chinese-speaking or region-specific context. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The document title and the entire content are written exclusively in Chinese, with no indication that language selection is optional or that the scope is explicitly limited to a Chinese-speaking or region-specific context. Under the policy rule for language/locale constraints, this can be considered a natural-language policy issue because it effectively fixes the skill content to a single language without opt-in.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The command-line interface defaults to search, which in this script means generating web-search queries for external standards rather than searching managed documents. That behavior does not align with the manifest's stated core functions of classification, version management, and template generation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.