Back to skill

Security audit

Cell 风格写作

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese writing-style helper with no executable code, persistence, credential handling, or hidden data access.

Install this if you want Codex to produce or review Chinese prose in Cell's specific voice. Users who want another language or a less personalized voice should explicitly override the language/style in their request.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (9)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The default contract says to 'Assume all of the following unless the user says otherwise' and includes 'write in Chinese.' This imposes a language choice by default rather than offering a language or locale option, which matches the policy's language/locale violation criterion.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill’s default prompt explicitly instructs the agent to produce Chinese output, but there is no indication that this language preference is conditioned on the user’s request or consent. This can override user expectations, degrade usability, and in multilingual contexts cause unintended disclosure or miscommunication, though it is not directly a code-execution or privilege-escalation issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The template headings and instructions are entirely in Chinese, which imposes a specific language on users without offering a language choice or opt-in. Under the policy, a skill should not force a specific language unless the locale constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The checklist explicitly requires output to be in Chinese and to match a specific Chinese stylistic voice ("像 Cell"). This is a natural-language locale policy constraint with no indication that users can choose another language or that the restriction is justified by a region-specific purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill content establishes a Chinese identity and phrase system as defaults, including Chinese labels and Chinese default catchphrases/emotional markers. This can force a specific language/locale in generated content without explicit user opt-in, which matches the policy's language/locale violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file includes a natural-language instruction that constrains output to a particular language/locale/style preference: 'it sounds like Cell, not generic casual Chinese.' The policy allows locale constraints only when users are given a choice or when the constraint is clearly documented and justified; neither is present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

Line L026 instructs writers to use the Chinese phrase “我的选择是” instead of “你应该,” which imposes a specific language/locale convention. Because the document does not offer an opt-in choice or explain that the skill is intentionally limited to Chinese-language output, this is 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
90% confidence
Finding

This markdown file contains user-facing natural-language fields exclusively in Chinese, and there is no indication that the skill is region-specific or that users may opt into another language. Under the policy rule for language or locale constraints, forcing a specific language without opt-in can be a policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

Lines L119-L121 provide example phrasing only in Chinese inside an otherwise English-language guidance document. This can impose a specific language/locale style without user opt-in, which matches the policy concern for language or locale constraints.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.