skills/sendaifun/skills/helius-dflow/Gen Agent Trust Hub

helius-dflow

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data from the Solana blockchain, creating a surface for indirect prompt injection.
  • Ingestion points: Digital asset metadata, wallet histories, and market titles are fetched via DAS and Wallet APIs in references/helius-das.md and references/helius-wallet-api.md.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are provided in the references.
  • Capability inventory: The agent can construct and submit transactions to the blockchain as described in references/helius-sender.md.
  • Sanitization: The skill relies on standard API parsing without additional logic to sanitize natural language content within data fields.
  • [EXTERNAL_DOWNLOADS]: The skill references and utilizes official SDKs and MCP servers from trusted organizations including Helius Labs and DFlow Protocol.
  • [COMMAND_EXECUTION]: Instructions are provided for installing MCP servers and using the Helius CLI for account management, which are standard operations for this developer toolset.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 06:15 PM