Back to skill

Security audit

discussion-cohesion-diagnosis

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow academic-writing diagnosis skill with no code execution, persistence, credential access, or hidden high-impact behavior.

Install this if you want diagnostic feedback on Discussion-section cohesion. Be aware that it is tailored to English psychology research papers and uses Chinese/bilingual reference guidance, so users outside that writing context may get less suitable feedback.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (7)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description says the skill triggers on phrases including "is my discussion connected" and "narrative flow check" followed by "etc.," which leaves the invocation boundary open-ended. Those phrases are generic enough to overlap with ordinary writing-help requests, and the file does not provide negative examples or explicit exclusion conditions to clarify when the skill should not activate.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The document consistently presents instructions and guidance in Chinese, with no indication that users may choose another language. If organizational policy requires not forcing a specific language without user opt-in, 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
82% confidence
Finding

The natural-language description states that the skill diagnoses the Discussion of an "English psychology research paper," which creates a language constraint. The file does not indicate that this is optional, user-selected, or justified as a region- or corpus-specific limitation, so it may violate language/locale policy expectations.

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 bilingual instructions and headings, which imposes a language/locale assumption on users without any stated opt-in or justification. The policy requires flagging language or locale constraints when the skill does not explicitly offer a choice or explain why the locale is required.

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 contains instructional content primarily in Chinese, with no indication that users may choose another language or that the resource is explicitly limited to a Chinese-speaking audience. Under the policy rule, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The usage section says to cite this example when a user's Discussion shows certain patterns, but the activation scope remains somewhat open-ended and lacks explicit negative examples or constraints about when not to invoke it. This can lead to over-application of the example beyond the intended cohesion-diagnosis context.

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 written as an official rubric, but it presents core instructions in a mixed Chinese-English format throughout the document. Because the skill does not indicate that bilingual output is optional or justified by a specific regional context, it may violate a language/locale policy that requires user choice or explicit documentation.

Content

No source excerpt is available for this finding.