r2js
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides an interface for executing arbitrary radare2 commands through
Session::raw_cmdand ther2cmdfunction. This is a core feature for binary analysis and manipulation. - [DYNAMIC_EXECUTION]: The skill enables
r2jsscripts, allowing for complex analysis tasks like ESIL emulation to be performed via JavaScript execution within the radare2 process. - [INDIRECT_PROMPT_INJECTION]: The skill processes analysis data such as flags and comments that may contain untrusted strings from analyzed binaries. Ingestion points: Untrusted data enters the agent context through queries to the 'comments' and 'flags' tables as described in
SKILL.md. Boundary markers: None are present in the provided examples to differentiate binary metadata from instructions. Capability inventory: The skill provides access tor2cmdfor analysis and binary patching. Sanitization: No sanitization or filtering of retrieved string data is documented.
Audit Metadata