molecular-psychiatry

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 process and analyze untrusted external data (manuscripts and study descriptions) to provide fit and formatting advice.
  • Ingestion points: The skill evaluates manuscript content, psychiatric genetics data, and neuroimaging findings provided by the user.
  • Boundary markers: The instructions do not specify the use of clear delimiters or guardrails to differentiate between user-provided manuscript text and the agent's core instructions.
  • Capability inventory: No dangerous tool capabilities, such as code execution or network requests to unknown domains, are requested in the skill manifest.
  • Sanitization: There are no instructions provided for sanitizing or escaping the user's manuscript content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 11:33 AM
Security Audit — agent-trust-hub — molecular-psychiatry