aave-planner
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local script
packages/plugins/aave-planner/scripts/simulate-position.tsusingnpx tsxto simulate financial positions. - [EXTERNAL_DOWNLOADS]: The skill references and links to
https://app.aave.comandhttps://docs.aave.com, which are official and well-known services for the Aave protocol. - [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it interpolates user-provided data into command-line arguments and deep link URLs.
- Ingestion points: User-provided inputs for
chainId,userAddress,action,token, andamountinSKILL.md. - Boundary markers: Absent. No delimiters are defined for user-controlled variables.
- Capability inventory: Execution of a simulation script and generation of web deep links.
- Sanitization: Absent. The skill does not define methods for validating or escaping user-provided inputs before they are used in commands or URLs.
Audit Metadata