send-tokens
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The skill constructs bash commands using variables like recipient addresses and memos to move financial assets. While high-risk, this is the primary purpose of the skill and uses a specific allowlisted tool.\n- [PROMPT_INJECTION] (LOW): Susceptible to Indirect Prompt Injection (Category 8) through ingestion of untrusted parameters.\n
- Ingestion points: recipientAddress, amount, tokenAddress, and memo fields defined in the bash snippets of SKILL.md.\n
- Boundary markers: No delimiters or 'ignore embedded instructions' warnings are present in the command templates.\n
- Capability inventory: Uses the
fdxtool to execute token transfers and check wallet balances across EVM and Solana chains.\n - Sanitization: No evidence of input escaping, shell-character filtering, or validation is provided in the skill instructions.
Audit Metadata