expression-language-injection

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides methodologies for executing shell commands such as 'id' and 'whoami' via EL injection. These are intended as payloads to verify Remote Code Execution on target systems.\n- [REMOTE_CODE_EXECUTION]: The instructions contain numerous Remote Code Execution payloads targeting SpEL, OGNL, and Java EL engines. These are informational and part of the skill's core purpose as an exploit methodology.\n- [SAFE]: The dangerous code patterns identified are illustrative examples for vulnerability research and security auditing. They are meant to be used by the agent against external targets and do not present a security risk to the agent itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 10:07 AM