pyzotero

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill ingests data from external sources (Zotero Web API and Semantic Scholar), including bibliographic metadata, abstracts, and full-text content from attachments. Ingestion points: Data is retrieved via API methods documented in references/read-api.md and references/mcp.md. Boundary markers: The provided instructions and templates lack explicit delimiters or instructions to ignore embedded commands within the ingested research data. Capability inventory: The skill includes file writing capabilities (zot.dump in references/files-attachments.md), network communication, and shell command execution (Bash tool in SKILL.md). Sanitization: No sanitization or filtering of external content is described in the skill instructions.
  • [EXTERNAL_DOWNLOADS]: The skill instructions specify the installation of the pyzotero library and its optional cli and mcp components from the Python Package Index (PyPI). These are well-known and expected dependencies for the skill's bibliographic management purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 02:14 AM