rag-service

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill facilitates the ingestion and retrieval of external, potentially untrusted content.
  • Ingestion points: The save method in SKILL.md allows documents from external sources to be stored.
  • Boundary markers: The client implementation does not demonstrate the use of delimiters or instructions to the agent to disregard instructions within retrieved text.
  • Capability inventory: The skill provides content that influences agent reasoning and decision-making by providing search results.
  • Sanitization: There is no evidence of sanitization or filtering for the retrieved text strings before they are returned to the agent context.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 02:53 AM