Skills
Navigate
skills/reason-machines/ai-agent-skills/litellm-agent-platform/Gen Agent Trust Hub

litellm-agent-platform

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions direct the user to clone the platform source code from a public repository.
  • Evidence: git clone https://github.com/LiteLLM-Labs/litellm-agent-platform.git in SKILL.md.
  • [INDIRECT_PROMPT_INJECTION]: The platform is designed to process external inputs through agents that have access to powerful tools, creating an inherent attack surface for indirect prompt injection.
  • Ingestion points: The /agents/{agentName}/runs API endpoint takes an input field containing user-supplied text (SKILL.md).
  • Boundary markers: No specific delimiting or instruction-shielding mechanisms are documented in the configuration examples.
  • Capability inventory: The agents are granted broad capabilities through MCP tools, including github, aws, filesystem, and database access.
  • Sanitization: The provided examples do not describe sanitization or validation logic for the input strings before they are processed by the agent harnesses.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 11:38 PM