annals-of-internal-medicine

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external, user-provided data (manuscripts) to provide feedback and submission advice.
  • Ingestion points: The manuscript content provided by the user to the agent for evaluation in SKILL.md.
  • Boundary markers: Absent; the skill does not specify delimiters or instructions for the agent to ignore potentially malicious instructions embedded within the user's manuscript.
  • Capability inventory: The skill is restricted to text analysis and advice generation. It does not contain capabilities for file writing, network operations, or code execution.
  • Sanitization: The skill does not define filters or sanitization logic for the processed manuscript text.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 11:33 AM
Security Audit — agent-trust-hub — annals-of-internal-medicine