using-riszotto

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses the uvx tool to download and run the riszotto package from the Python Package Index (PyPI), which is a well-known and standard package registry.
  • [COMMAND_EXECUTION]: Shell commands are used to invoke the riszotto CLI for library management tasks such as searching, indexing, and exporting citations.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it processes external data from a Zotero library.
  • Ingestion points: Untrusted content from Zotero PDF attachments is converted to markdown and ingested into the agent context via the 'uvx riszotto show' command.
  • Boundary markers: The instructions do not provide explicit delimiters or boundary markers to isolate the converted PDF text from the agent's system instructions.
  • Capability inventory: The agent has the capability to execute further shell commands using the uvx tool as described across the skill's workflows.
  • Sanitization: There is no mention of sanitization, filtering, or validation of the content retrieved from the Zotero library before it is displayed to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 09:14 AM