obsidian-plugin-templater

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt shows collecting/using API tokens (e.g., setting apiToken = "your_api_token_here" and interpolating it into an Authorization header) and demonstrates using tp.system.prompt and tp.obsidian.request with headers, which would require the LLM to embed secret values verbatim into generated code/requests.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly shows use of tp.obsidian.request / tp.obsidian.requestUrl to fetch arbitrary external URLs (see "HTTP 请求" and examples assigning responseText to tR) and warns that externally sourced template strings may be re-executed, so untrusted web content can be ingested and influence template execution and subsequent actions.