obsidian-vault-add

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

• Third-party content exposure detected (high risk: 0.85). The skill performs runtime web lookups for metadata and cover art (e.g., Open Library search JSON, iTunes Search API, TVMaze API, Wikipedia REST API) and then ingests returned fields/descriptions into the note/LLM context, which is outsider-authored free text from public web sources.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)