solana-agent-kit
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill documentation describes an autonomous agent loop that presents an indirect prompt injection attack surface.
- Ingestion points: The
agent.analyzemethod inSKILL.mdis designed to ingest external context and market conditions. - Boundary markers: The example implementation lacks explicit delimiters or instructions to ignore embedded commands in the processed data.
- Capability inventory: The agent has access to sensitive capabilities including
transfer,trade,deployToken, andlistNFTacross several plugins. - Sanitization: The provided patterns do not include sanitization or validation of the input context before it is passed to the language model for decision-making.
- [COMMAND_EXECUTION]: The skill enables agents to autonomously execute high-impact blockchain operations such as fund transfers and token swaps, which carry inherent risk if the agent's decision-making process is compromised.
- [EXTERNAL_DOWNLOADS]: The guide instructs users to download and install several third-party packages from the Solana Agent Kit ecosystem, including
solana-agent-kit,solana-mcp, and various modular plugins.
Audit Metadata