Back to skill

Security audit

results-cohesion-flow-checker

Security checks for vulnerabilities and agentic risk

Overview

This is a focused writing-review skill with Chinese reporting materials and no evidence of unsafe code, persistence, credential access, or hidden behavior.

Install this if you want Chinese-language feedback on cohesion and flow in English Results sections. Users who need English output should confirm or request that separately, because the bundled report template is Chinese.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (6)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file presents core user-facing instructions in Chinese while the skill is scoped to checking English papers, creating a language expectation that is not user-selectable. Under the policy, forcing a specific language or locale without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown template is entirely written in Chinese and prescribes Chinese section headings and content labels throughout, which imposes a specific language on skill output. The policy allows locale constraints only when the skill offers user choice or clearly documents a justified region-specific requirement, neither of which appears in this file.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file contains bilingual instructions and examples, including a Chinese title and usage guidance alongside English terminology, but it does not state that the skill is intentionally bilingual or let the user choose a preferred language. That can violate language/locale policy when users are forced into a mixed-language experience without opt-in.

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
91% confidence
Finding

The title explicitly presents the examples library in Chinese, and the document consistently uses Chinese instructional text for explanations and labels. Because this is a general examples file rather than a clearly region-specific compliance or locale-bound skill, the file appears to impose a specific language without offering the user a choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file is primarily written in Chinese and presents the rubric content as fixed-language guidance, with no indication that users may choose another language or that the skill is limited to a Chinese-language context. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.