fetch-preprint-recent

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches preprint metadata and abstracts from the official bioRxiv/medRxiv public API.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted research data from external servers.
  • Ingestion points: Research abstracts and titles are fetched from bioRxiv and medRxiv (SKILL.md).
  • Boundary markers: None identified in the prompt templates.
  • Capability inventory: Performs file writes to the local .cache/ directory and returns content to the agent context (SKILL.md).
  • Sanitization: The skill normalizes the data structure but does not specify sanitization or escaping of the research text.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 02:08 AM
Security Audit — agent-trust-hub — fetch-preprint-recent