Back to skill

Security audit

method-conventions-diagnostic

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only academic writing diagnostic skill with no executable code, persistence, credential use, or hidden data flow.

Before installing, confirm you want a Chinese-language diagnostic workflow and that your environment has the referenced textbook/source materials if you expect full evidence matching. The package does not appear to run code or access credentials, but some documented paths do not match the packaged files exactly.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (13)

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest description is written as a fixed Chinese-language behavior description and does not state that the user may choose another language. Under the policy rule for natural-language constraints, forcing a specific language without opt-in is a violation unless clearly documented as a justified region-specific tool.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The fixed output format mandates a Chinese diagnostic report structure and headings, but nowhere gives the user an option to select language. This is a natural-language policy issue because the skill enforces a locale/language in its user-facing output.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

Line L456 states '本 Skill 仅诊断,不改写', which frames the skill as limited to issue identification and suggestions only. But the required report template later includes multiple explicit rewrite options with ready-to-use sentence formulations (e.g., L354-L356, L369-L371, L384-L386), so the documentation actively contradicts the actual prescribed behavior.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The document headings and explanatory text are written entirely in Chinese while embedding an English source excerpt, with no indication that language selection is optional or constrained by a specific regional requirement. This can violate a language/locale policy when users are not given an opt-in or alternative language path.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The title and the entire rubric are written in Chinese, signaling a fixed language/locale for the skill content. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified, which is not present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The headings and diagnostic guidance are written entirely in Chinese, which constitutes a natural-language locale choice embedded in the file. There is no indication that the skill offers an opt-in, alternative language, or a region-specific justification for requiring Chinese.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file uses Chinese throughout its headings and guidance, which can function as a natural-language policy constraint if users are expected to consume or apply the skill in that language. The file does not indicate that language selection is optional or that the locale restriction is intentionally limited to a Chinese-speaking context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This markdown file presents instructional/contextual content in two languages, but does not indicate any user opt-in or language selection. Under the language/locale policy rule, forcing or assuming a language without explicit choice can be a natural-language policy concern.

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 presents the skill content entirely in Chinese, including the heading and diagnostic guidance, with no indication that users may choose another language. Under the policy rule for language/locale constraints, this can be a natural-language policy violation when a specific language is imposed without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The file’s headings and explanatory text are entirely in Chinese, while the embedded source excerpt is in English. There is no indication that the skill is region-specific or that users can opt into this language/locale behavior, which may violate a language-choice policy.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file’s headings, labels, and explanatory guidance are written entirely in Chinese, while the cited source material is in English. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is explicitly justified, which is not present here.

Content

No source excerpt is available for this finding.