literature-mentor

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches academic paper metadata and full-text content from Zotero and external repositories such as arXiv using the Zotero MCP and web search tools. These operations are integral to the skill's primary function and target well-known academic services.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) because it processes untrusted data from retrieved academic papers.
  • Ingestion points: Paper content is ingested via zotero_get_item_fulltext and web_fetch (documented in SKILL.md).
  • Boundary markers: The prompt instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when the agent processes the retrieved text.
  • Capability inventory: The skill utilizes search and retrieval tools (Zotero, web_search, web_fetch) but does not include capabilities for arbitrary command execution or persistence.
  • Sanitization: No explicit sanitization or filtering of the retrieved paper content is defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 04:47 PM
Security Audit — agent-trust-hub — literature-mentor