Description
PPTAgent is an agentic framework for reflective PowerPoint generation. Prior to commit 418491a, PPTAgent is vulnerable to arbitrary code execution via Python eval() of LLM-generated code with builtins in scope. This issue has been patched via commit 418491a.
Problem types
CWE-95: Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection')
Product status
References
github.com/...TAgent/security/advisories/GHSA-89g2-xw5c-v95p
github.com/...TAgent/security/advisories/GHSA-89g2-xw5c-v95p
github.com/...ommit/418491a9a1c02d9d93194b5973bb58df35cf9d00