gut

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 untrusted user-provided data (manuscripts and research summaries) to evaluate their fit for the journal Gut.
  • Ingestion points: The agent is expected to process the author's manuscript content provided during the chat session.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the ingested manuscript text.
  • Capability inventory: The skill instructs the agent to read local documentation files (source-basis.md, official-source-map.md) and perform web searches for live submission guidelines. It does not utilize capabilities for file writing, credential access, or arbitrary command execution.
  • Sanitization: There are no requirements for escaping or validating the content of the user-provided manuscript before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 11:33 AM
Security Audit — agent-trust-hub — gut