Back to skill

Security audit

method-cohesion-diagnostic

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only academic writing diagnostic skill with no hidden execution, credential access, persistence, or destructive behavior.

Install this if you want a Chinese-language diagnostic report for psychology Method-section cohesion. Be aware it expects local reference/example files and may refer to a Windows PDF path; it should not need credentials, network access, background execution, or write access for normal use.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (17)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description is entirely in Chinese and specifies the skill's diagnostic behavior and outputs, but nowhere in the file is there an option for the user to choose another language or an explanation that the skill is intentionally restricted to Chinese users. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The fixed output format mandates Chinese section headings and Chinese report structure, which effectively constrains all responses to Chinese. Because the file does not provide a language-selection mechanism or clearly justify a locale-specific restriction, this conflicts with the language/locale policy.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The title and the entire checklist are written in Chinese, presenting the skill as inherently Chinese-language without any visible opt-in, alternative locale, or explanation that it is limited to a Chinese-speaking context. Under the policy rule, forcing a specific language without user choice 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
88% confidence
Finding

The entire skill file is written as a Chinese-only template/example and does not indicate that other languages are supported or that Chinese is optional. Under the policy rule for language/locale constraints, forcing a specific language without user opt-in 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
96% confidence
Finding

This markdown file presents headings and instructional content entirely in Chinese, including the skill framing and adaptation guidance, with no indication that users can choose another language. Under the policy rule, forcing a specific language without opt-in is a natural-language locale violation unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file presents headings and instructional content only in Chinese, with no indication that users may choose another language or that the locale restriction is intentional. Under the policy, forcing a specific language without user opt-in 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
88% confidence
Finding

This markdown file contains user-facing instructional content in Chinese while the quoted source passage is in English. Because the file does not state that the skill is intentionally Chinese-only or offer a language/locale choice, it may violate the language/locale policy requiring user opt-in or clear justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown file contains user-facing text in both Chinese and English, but it does not indicate whether the language choice is intentional, optional, or user-selectable. Under the language/locale policy rule, forcing or assuming a language without opt-in 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
90% confidence
Finding

This markdown file presents its headings and instructional framing entirely in Chinese, with no indication that users can choose another language or that the locale restriction is required for a region-specific purpose. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

md
## 原文片段

At T0, participants first provided informed consent and basic demographics. At T1, 132 days after T0 on average, participants first completed the mind game to measure dishonest behavior, followed by other behavioral paradigms that are beyond the scope of the current investigation. At T2, 168 days after T0 and, thus, 34 days after T1 on average, we again measured dishonest behavior, now using the coin-toss task. Finally, T3 took place 1,258 days (∼3 years and 5 months) after T0 and, thus, 1,090 days (∼3 years) after T1 and 1,056 days (∼2 years and 11 months) after T2 on average. Here, we implemented a lottery task inspired by the randomized response technique to measure dishonest behavior.

## 来源文献

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · references/checklist.md (reported line 54)May include surrounding context.

md
## 原文片段

At T0, participants first provided informed consent and basic demographics. At T1, 132 days after T0 on average, participants first completed the mind game to measure dishonest behavior, followed by other behavioral paradigms that are beyond the scope of the current investigation. At T2, 168 days after T0 and, thus, 34 days after T1 on average, we again measured dishonest behavior, now using the coin-toss task. Finally, T3 took place 1,258 days (∼3 years and 5 months) after T0 and, thus, 1,090 days (∼3 years) after T1 and 1,056 days (∼2 years and 11 months) after T2 on average. Here, we implemented a lottery task inspired by the randomized response technique to measure dishonest behavior.

## 来源文献

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · references/examples/cohesion_Thielmann_2025_5.md (reported line 5)May include surrounding context.

md
## 原文片段

At T0, participants first provided informed consent and basic demographics. At T1, 132 days after T0 on average, participants first completed the mind game to measure dishonest behavior, followed by other behavioral paradigms that are beyond the scope of the current investigation. At T2, 168 days after T0 and, thus, 34 days after T1 on average, we again measured dishonest behavior, now using the coin-toss task. Finally, T3 took place 1,258 days (∼3 years and 5 months) after T0 and, thus, 1,090 days (∼3 years) after T1 and 1,056 days (∼2 years and 11 months) after T2 on average. Here, we implemented a lottery task inspired by the randomized response technique to measure dishonest behavior.

## 来源文献

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · references/rubric.md (reported line 80)May include surrounding context.

md
## 原文片段

At T0, participants first provided informed consent and basic demographics. At T1, 132 days after T0 on average, participants first completed the mind game to measure dishonest behavior, followed by other behavioral paradigms that are beyond the scope of the current investigation. At T2, 168 days after T0 and, thus, 34 days after T1 on average, we again measured dishonest behavior, now using the coin-toss task. Finally, T3 took place 1,258 days (∼3 years and 5 months) after T0 and, thus, 1,090 days (∼3 years) after T1 and 1,056 days (∼2 years and 11 months) after T2 on average. Here, we implemented a lottery task inspired by the randomized response technique to measure dishonest behavior.

## 来源文献

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file uses Chinese headings and explanatory text throughout, with no indication that users may choose another language. Under the stated 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
90% confidence
Finding

This markdown file presents its headings and evaluative guidance entirely in Chinese, which can indicate a fixed language requirement for the skill content. Under the policy, language constraints should either offer user opt-in/choice or be clearly documented as justified for a specific locale or use case, 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
90% confidence
Finding

The file presents all instructional headings and diagnostic guidance in Chinese, which constitutes a language-specific constraint in natural-language content. There is no indication that the user can choose another language or that the locale restriction is required for a documented region-specific purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This file contains user-facing natural-language instructions in a single language, beginning with a Chinese title and continuing throughout the rubric. Under the locale-policy rule, forcing a specific language without user opt-in can be a policy concern when no alternative language option or justification is provided.

Content

No source excerpt is available for this finding.