obsidian
Use this skill whenever the user wants to work with Obsidian in any capacity. This is the ONLY skill for Obsidian vaults, .base files, Obsidian Markdown, Obsidian plugins, and Obsidian Web Clipper. Trigger for: creating or editing notes with wikilinks, callouts, embeds, or frontmatter; building or debugging .base files (formulas, filters, views, YAML quoting); Obsidian plugin development or hot-reload; Web Clipper JSON templates or AI Interpreter prompts; vault structure, daily notes, or the obsidian CLI. Also trigger when the user describes Obsidian-specific problems without naming Obsidian — like .base YAML errors, foldable callout syntax, base formula for tasks due this week, or clipper template for arxiv. Do NOT trigger for Logseq, Notion, Dataview plugin queries, generic markdown processing scripts, or general-purpose Chrome extensions.
75
92%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Security
2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Third-party content exposure detected (high risk: 1.00). The skill's Web Clipper workflow explicitly requires using WebFetch to retrieve and analyze live page content from user-provided/reference URLs (see SKILL.md "Fetch & Analyze Reference URL: (REQUIRED) Use WebFetch..." and references/clipper-analysis-workflow.md), meaning the agent will ingest untrusted public web pages whose content can influence template generation and follow-up actions.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
Potentially malicious external URL detected (high risk: 0.80). The skill requires a runtime WebFetch of user-supplied pages (example: WebFetch(url="https://example.com/recipe/chocolate-cake")) to extract page HTML/JSON-LD and populate clipper variables (e.g., {{content}}, {{selector:...}}) which can be used in templates and AI Interpreter prompt variables, meaning external page content fetched at runtime can directly influence prompts and template logic.
- Repository
- seanGSISG/claude-depot
- Commit
dd10cc1
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.