sympy

Warn

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the autowrap and ufuncify utilities in references/code-generation-printing.md to generate and compile C or Fortran source code at runtime, which involves the dynamic execution of generated code via system compilers.
  • [COMMAND_EXECUTION]: The reference file references/code-generation-printing.md provides examples for using pickle.load() to deserialize expressions, an unsafe operation that can lead to arbitrary code execution if the data source is malicious.
  • [PROMPT_INJECTION]: The skill provides ingestion points for untrusted strings through parsers like parse_expr and parse_latex in references/code-generation-printing.md. These parsers operate without boundary markers or sanitization, and when combined with the skill's capabilities (such as file-writing and runtime compilation), they create a surface for indirect prompt injection and logic manipulation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 20, 2026, 09:49 AM
Security Audit — agent-trust-hub — sympy