nejm

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided clinical medicine manuscripts and research data to determine journal fit.
  • Ingestion points: User-provided manuscript text, trial data, and research summaries are processed in the agent context during fit/venue-selection tasks.
  • Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the processed manuscript content.
  • Capability inventory: No high-privilege capabilities such as arbitrary shell execution, network exfiltration tools, or sensitive file write operations were identified in the skill configuration.
  • Sanitization: There are no explicit instructions for the agent to sanitize or escape instructions that might be embedded within user-provided clinical documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 11:33 AM
Security Audit — agent-trust-hub — nejm