sci-zotero

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes an external Python script located at ../../scripts/zotero.py to perform library operations such as listing items and adding citations.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it ingests bibliographic metadata from external sources.
  • Ingestion points: Bibliographic data such as paper titles, abstracts, and author names fetched via DOI, ISBN, PMID lookups or from the Zotero API.
  • Boundary markers: None identified; the skill does not provide instructions to the agent to treat data from these external sources as untrusted or to ignore embedded commands.
  • Capability inventory: The skill can execute local scripts (zotero.py) with arguments derived from user input or external data.
  • Sanitization: None identified; there is no mention of validation or sanitization of the data retrieved from external bibliographic databases.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 02:11 PM
Security Audit — agent-trust-hub — sci-zotero