langgraph-orchestration
Fail
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The provided code for the
calculatetool uses theeval()function to process theexpressionargument. In an AI agent environment, this is a critical risk because the LLM—which generates the tool parameters—can be manipulated via prompt injection to execute arbitrary Python code.\n - Evidence:
return eval(expression)in thecalculatetool function inskill.md.\n- [COMMAND_EXECUTION]: Exploiting theeval()vulnerability allows an attacker to execute operating system commands (e.g., using__import__('os').system()), which could lead to full system compromise or data exfiltration.\n- [EXTERNAL_DOWNLOADS]: The skill recommends installinglanggraphandlangchain-openaiviapip. These are well-known and trusted packages from established organizations.
Recommendations
- AI detected serious security threats
Audit Metadata