t2000-swap
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill metadata specifies a requirement for the @t2000/cli package to be initialized via npx, which fetches and executes code from the npm registry. This is consistent with the skill's branding and primary purpose.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (t2000 swap) to perform on-chain cryptocurrency transactions.
- [PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection due to its handling of untrusted data. 1. Ingestion points: User-provided values for token names, amounts, and slippage percentages are used directly as arguments in the t2000 CLI command. 2. Boundary markers: The skill does not use any delimiters or specific instructions to isolate these inputs or warn the agent to ignore instructions embedded within them. 3. Capability inventory: The skill enables shell command execution via the t2000 tool, which has the capability to perform financial transactions. 4. Sanitization: No sanitization or validation steps are defined in the skill markdown to check the integrity of user inputs before they are passed to the CLI.
Audit Metadata