skills/sepehr071/iran-mcp/swapwallet/Gen Agent Trust Hub

swapwallet

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data retrieved from external wallet APIs, creating a surface for indirect instructions to influence the agent. Ingestion points: Wallet data including transaction history and contact names are fetched via tools like get_transactions and get_contacts (SKILL.md). Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat external content as untrusted data. Capability inventory: The skill can trigger financial action requests such as request_transfer and request_crypto_withdraw (SKILL.md). Sanitization: No sanitization or validation of the external strings is described.
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for connecting to an external MCP server at https://swapwallet.app/mcp. This is the expected behavior for integrating with the SwapWallet platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 05:31 AM