cell-reports-medicine

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill content is restricted to academic writing guidance and does not contain signs of prompt injection, obfuscation, credential theft, or persistence mechanisms.- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves processing user-supplied manuscripts, which presents an inherent surface for indirect instruction processing.
  • Ingestion points: User-provided manuscript abstracts and clinical study data processed in SKILL.md.
  • Boundary markers: The skill does not implement specific delimiters for user content, but it includes clear instructions that official journal site information takes precedence over the skill's local logic.
  • Capability inventory: Instructions direct the agent to read local resource files and perform web searches for live submission guidelines.
  • Sanitization: No explicit sanitization of user-provided study data is specified in the prompt logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 11:33 AM
Security Audit — agent-trust-hub — cell-reports-medicine