cli-anything-zotero
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides numerous commands that interact with the local Zotero application, its Local API, and its SQLite database. These include app management (
launch,enable-local-api), data retrieval, and experimental SQLite write operations. - [INDIRECT_PROMPT_INJECTION]: The skill acts as a data ingestion point for the agent.
- Ingestion points: Commands such as
item get,item context, andnote get(described inSKILL.md) retrieve data from a user's Zotero library, which often contains content imported from untrusted web sources. - Boundary markers: There are no explicit instructions or delimiters defined to separate retrieved Zotero data from agent instructions.
- Capability inventory: The skill allows for local file system access (Zotero attachments) and experimental database writes (
SKILL.md). - Sanitization: No sanitization or validation mechanisms are described for the data retrieved from Zotero before it is processed by the agent.
Audit Metadata