other
- Location
SKILL.md:27- Finding
Excessive Persistent Collection of Personal and Conversational Data
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This memory-management skill is not malware, but it encourages broad long-term storage of personal details and conversation logs without clear consent or deletion controls.
Install only if you are comfortable with the agent creating persistent workspace memory files. Before using it, require explicit consent before saving user details, avoid raw conversation logs, remove contact information unless essential, redact private data beyond API keys, and define review, deletion, and retention rules for the memory directory.
SKILL.md:27Excessive Persistent Collection of Personal and Conversational Data
The description declares trigger words including “记忆管理” and “记忆分类” without constraining context, scope, or exclusion cases. These phrases are generic enough that ordinary discussion about memory organization could unintentionally invoke the skill.
The skill explicitly encourages storing user identity, preferences, and background information, but it does not require user consent, notice, minimization, or a retention policy tied to privacy expectations. This creates a real privacy and data-protection risk because an agent may persist personal data users did not expect to be stored long-term, increasing exposure in later sessions or shared workspaces.
The instruction to write interesting daily conversations into raw logs encourages retention of free-form natural-language content that can easily include secrets, personal data, internal URLs, credentials, or sensitive business context. Even with some token-pattern scanning elsewhere, raw conversational logs are hard to sanitize reliably, so this materially increases the risk of data leakage, over-retention, and later unintended disclosure.
Describing daily logs as a place where 'everything' is recorded normalizes indiscriminate data collection and conflicts with the earlier principle of selective memory storage. In practice, this leads to over-collection of user-provided data, including sensitive or regulated information, and broadens the blast radius if the memory directory is later accessed by other sessions, agents, or users.
This markdown template is written entirely in Chinese, including field values and section labels, with no indication that users may choose another language. That creates a natural-language policy concern because it imposes a specific language by default without opt-in or a stated region-specific justification.
This template is entirely written in Chinese, including the name, description, heading, and field labels, with no indication that the user can choose another language. That can violate a language/locale policy when a skill or template forces a specific language without user opt-in or documented justification.
This markdown template is primarily written in Chinese, but L17 introduces an English section header. The file does not indicate that language choice is optional or user-selectable, so it may violate language/locale consistency policy by implicitly forcing mixed-language output.
The template’s visible field values and section content are entirely in Chinese, which implies a fixed output language for users of this skill artifact. There is no accompanying note that the language is optional, user-selectable, or required for a specific regional/compliance context.