Back to skill

Security audit

Justin writing style

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese narrative-style writing skill with no executable code, network behavior, credential access, or destructive actions found.

Install this only if you want a Chinese-language prose style generator. Review the broad trigger phrases if your agent frequently handles general writing requests, and ensure your installer does not import the hidden .workbuddy memory note as global memory.

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
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (14)

YARA rule 'privilege_escalation_tools': Privilege escalation tools and techniques [hacktools]

High
Category
YARA Match
Confidence
75% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · justin-writing-style.png (reported line 1121)May include surrounding context.

text
�~H�+KzEo��
��d��"���V�͎��~�L"�L��"��˗n]a�L`8RJE�D��Ҁ�����(��13'�(�Jf�<@�4��"�Ǣ:�8\�K�!a��D�N�z�HNV���f1�UM�c���y;�o~�fv�C��1�t��-TyLM&)�\����!���}zMr�Ң� �Z;,�c��>�@y�x���Ϙ��m�������`s{=��s���bų
������(�Hrd/_��7���^$Y�`e�p�\q������km��w��˟��2 �t>�>~����_�˖��ˈIE����2�)Ldۡ�~J&�6�"S���P�G�B�NT��]��p�08�@�l��ڃd�AIc���~;nc('$�Pspy9F�e`EK޻�ی��0���c���繸�|[X�!"�h��P�F0�	�Rsf�˄)<�c�n�s���$[��kւ2���1�@7��ҳ?��η�:d�
ķ�7��l�m��Vט*D,2���9'�-��pkn��`s#�1�����DnkE�N%��`w��y(3!7x�>vIv9��3]S�I�l��ӷ���?�c�1(������b�q��T42,�"�
���i�w uq��ËW���Eu��=ݣ�Vs��Pյv��0G�="�q��L�f�I��d����m`�!0�QL@�pUJ�zXyo#"TǮȘ�v�g�:
�L���ͱO�s=��8�\DF��g����;"�<�c�"r��1��q^31��"��8�MDƘ��P�/�\��D�-#"�v{9n�2�2�,��a��:&L�׹EDY���d�������v�w��232l;WoD��K)�M2#N��s*��M����,,DE��\F��� ~Fd��%Gĕ�d&6oF�
�����]�U�cL�RE�e�#���v?@(��_E�-�R���^�g��%&/�-�Hߦ���o�c�YlŲ��j�DlVU�

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The changelog content is written in Chinese and presents project conventions in that language without any indication that users may choose another language or locale. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list contains several generic phrases such as 冷叙述写作, 极简叙事体, 自述体长文, and viral essay that can match ordinary writing requests unrelated to this narrowly scoped style. Over-broad activation can cause unintended skill invocation, steering users into a constrained narrative mode and bypassing more appropriate general-purpose or safer writing behaviors.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description and role instructions repeatedly specify producing "中文叙事文本" and position the skill as a Chinese narrative creator, but do not state that this language restriction is optional or user-selectable. Under the policy, forcing a specific language without opt-in is a natural-language policy concern unless the locale constraint is explicitly justified.

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 audit/report is written entirely in Chinese, including headings, status labels, and deployment guidance, with no indication that language selection is optional or user-driven. The policy specifically flags language or locale constraints when a skill forces a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file contains natural-language instructional content exclusively in Chinese, and there is no indication that the skill is region-specific or that users can opt into this language. Under the policy rule, forcing a specific language without user choice can be a locale/language policy violation.

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 content is written exclusively in Chinese, including the title and all instructional text, with no indication that users can opt into another language or that the skill is intentionally limited to a Chinese-language audience. 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

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file is entirely written in Chinese and presents the examples and explanations only in that language. Under the policy rule, a skill that imposes a specific language without user opt-in or documented justification can be 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
91% confidence
Finding

The document gives prescriptive workflow instructions entirely in Chinese and requires specific critique and revision behavior, but it does not indicate that the skill is intentionally Chinese-only or offer any language/locale opt-in. Under the policy rule, forcing a specific language without user choice is a natural-language locale violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file contains prescriptive natural-language instructions entirely in Chinese and requires specific Chinese writing constraints such as sentence length in characters and exact Chinese phrasing examples. Because the guidance is framed as mandatory runtime behavior and does not offer a user language/locale choice, it creates a language policy constraint that may conflict with broader user-preference requirements.

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 is entirely a prescriptive style guide in Chinese and uses mandatory language such as '不许凭感觉偏离' and '规则' to enforce a specific linguistic style. Because it does not provide any user opt-in, language choice, or region-specific justification, it constitutes a natural-language locale policy concern under the language/locale rule.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file is entirely framed as a Chinese-only output template and repeatedly specifies Chinese-form formatting and style requirements, but it does not provide any opt-in, fallback, or user choice for language/locale. 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
91% confidence
Finding

This markdown file is entirely written in Chinese and all examples, instructions, and evaluation criteria assume Chinese-language operation. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly justified, which is not stated here.

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 all instructions and examples exclusively in Chinese, and there is no natural-language indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the stated policy, forcing a specific language without user opt-in is a locale-policy concern.

Content

No source excerpt is available for this finding.