T05 · Unauthorized Access and Privilege Escalation
- Location
SKILL.md:8- Finding
Excessive Command-Execution Permissions Violate Least Privilege
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
The skill is coherent for investor education, but it asks for broad command/write authority and stores customer content persistently without clear consent or sanitization.
Install only in a sandboxed workspace with no unrelated files or secrets exposed. Treat customer questions and feedback as sensitive: require explicit consent before saving, redact personal or account-specific details, and review changes before they enter the reusable knowledge base. Prefer a version that removes Bash/Exec and scopes Write to the investor-education knowledge directory.
SKILL.md:8Excessive Command-Execution Permissions Violate Least Privilege
SKILL.md:84Untrusted Customer Content Is Persisted and Reused Without Sanitization
The README presents all user-facing invocation examples, workflow descriptions, and operational guidance solely in Chinese. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified or alternatives are offered.
The trigger conditions are overly broad and can activate on many generic explanation or writing requests, causing this skill to run outside its intended scope. In context, that matters because the workflow can perform web access and file writes, so accidental invocation may lead to unnecessary data collection, content generation, or repository modification.
The workflow directs the agent to write generated content, customer feedback, and metadata back into local knowledge-base files without requiring explicit user consent. This is dangerous because a user asking only for content generation may unknowingly trigger persistent local state changes, enabling prompt-to-file injection, corruption of the knowledge base, or unauthorized retention of user-provided material.
The skill instructs storage of customer Q&A, feedback, and usage frequency in a knowledge base with no minimization, redaction, or sensitivity screening. In this context, investor-education conversations can easily contain personal financial details, contact information, or regulated communications, so indiscriminate retention increases privacy, compliance, and data-leak risk.
The manifest description is entirely in Chinese and presents the skill as Chinese-language investor education workflow content without offering any user language choice or noting that the skill is region- or language-specific. Under the policy, language or locale constraints should be opt-in or clearly justified.
The document is entirely written in Chinese and all example prompts are Chinese-language prompts, which indicates the skill workflow is oriented toward a single language. There is no natural-language indication that users may choose another language or that the locale restriction is intentional and justified for a region-specific tool.
This markdown file contains user-facing natural-language content exclusively in Chinese, but provides no indication that the skill offers a language choice or that Chinese is a justified locale-specific requirement. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.
The prompt explicitly routes content to公众号/WeChat publishing ('调用 expression-layer (writes + wechat) -> 交付') without any confirmation, warning, or boundary between drafting and external posting. In an agent workflow, this can cause unintended real-world actions such as publishing content to an external channel when the user may only want drafting assistance, creating reputational and operational risk.
This markdown file presents all instructions and descriptions exclusively in Chinese, and there is no indication that users may choose another language or that the file is intentionally limited to a Chinese-only audience. Under the policy, forcing a specific language without opt-in is a natural-language policy violation.
The file’s natural-language content is entirely in Chinese and presents the prompt/expected behavior only in that language, with no indication that users may choose another language. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.
The document presents all instructions and guidance 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-only audience. This can violate language/locale policy where skills should not force a specific language without user opt-in or explicit justification.
The document explicitly describes pushing knowledge-base content to 'all related customers' based on advisor usage records and customer FAQ statistics, but it provides no guardrails around consent, audience qualification, opt-out handling, or review for suitability. In an investor-education workflow, broad proactive outreach can create privacy, compliance, and mis-targeting risks, especially if internal usage data is used to drive distribution decisions.
The entire template is written to require Chinese-language output, including all section headers and content placeholders, but it does not state that language selection is optional or limited to a justified Chinese-only context. This can violate language/locale policy when the skill is used in environments where users have not opted into Chinese output.
The file frames the prompt and requested article entirely in Chinese and specifies a WeChat public-account publishing context, implying a fixed language/locale. There is no indication that the user can choose another language or that the Chinese-only constraint is explicitly documented as a justified regional requirement.
This markdown file contains user-facing natural-language instructions exclusively in Chinese, including the expected routing behavior and output description. Because no alternative language option or opt-in is mentioned, this may constitute a language/locale policy violation under the requirement to avoid forcing a specific language without user choice.
This markdown file presents all instructional content in Chinese and does not indicate that the user can choose another language or that the skill is intentionally restricted to a Chinese-speaking audience. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.