Security audit
Security checks for vulnerabilities and agentic risk
This skill is a coherent Obsidian note-writing helper, but users should be mindful that it can persist conversation details, source links, and user-approved sensitive text into a vault.
Install this if you want Chinese-structured Obsidian notes and are comfortable granting the agent vault write/read access. Avoid saving live API keys, cookies, bearer tokens, private invite links, or tokenized URLs in notes, especially if your vault syncs or is shared. Review generated notes before write-back when the source material contains confidential project or meeting content.
The manifest description is written entirely in Chinese and frames the skill's behavior in that language, with no indication that users may choose another language. Under the policy, locale or language constraints should be optional or clearly justified; this file does not provide such an opt-in or justification.
The instruction explicitly allows writing secrets such as API keys, cookies, tokens, auth codes, or bearer values into persistent notes when a user asks. In the context of an Obsidian note-writing skill, this is dangerous because it normalizes long-term plaintext storage of credentials in a knowledge base that may be synced, indexed, backed up, or accidentally shared, greatly increasing exposure risk.
The skill enables implicit invocation without any visible activation constraints, so the agent may trigger it based on broad conversational cues rather than explicit user intent. Because this skill writes or structures persistent Obsidian notes from conversations and project material, an over-broad trigger can cause unintended data capture, summarization, or persistence of sensitive content.
The template and instructions are presented in Chinese, which effectively imposes a language choice on users. There is no opt-in, alternative language option, or documented justification that this skill is intentionally limited to a Chinese-speaking context.
The title and entire instruction set are written in Chinese and present the workflow as the required default, with no indication that users may choose another language or locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.
This markdown file contains a natural-language requirement that titles and body text display correctly in Chinese, implying the skill expects or enforces Chinese output. Under the policy, forcing a specific language without user opt-in is a locale policy violation unless the constraint is explicitly justified, which is not present here.
The template explicitly instructs preserving user-provided URLs in the note without any privacy or sensitivity check. URLs can contain personal data, access tokens, internal endpoints, tracking parameters, or confidential document links, so blindly retaining them can cause unintended disclosure when notes are synced, shared, or indexed.
No suspicious patterns detected.
