Direct insertion of unescaped user input into template-rendering tools allows arbitrary code execution via specially crafted agent instructions.
The create_agent_centric_tools() function returns tools (like acp_create_file) that process file content using template rendering. When user input from agent.start() is passed directly into these tools without escaping (as shown in agent_centric_example.py:85-86), template expressions in the input are executed rather than treated as literal text. This occurs because:
1. No input sanitization or escaping is applied to user-controlled content
2. The ACP-enabled runtime auto-approves operations (approval_mode="auto")
3. Tools lack context-aware escaping for template syntax
# Replace the agent.start() call at line 85 with:
result = agent.start('Create file with content: {{ self.__init__.__globals__.__builtins__.__import__("os").system("touch /tmp/pwned") }}')
Successful exploitation creates /tmp/pwned confirming arbitrary command execution. The expression {{7*7}} renders as 49 instead of literal text.
Attackers can execute arbitrary system commands with the privileges of the running process by injecting malicious template expressions through agent instructions. This compromises the host system, enabling data theft, ransomware deployment, or lateral movement.
{{ }}) in user input using Jinja2 autoescape=True{
"cwe_ids": [
"CWE-94"
],
"severity": "HIGH",
"github_reviewed": true,
"nvd_published_at": "2026-04-08T21:17:01Z",
"github_reviewed_at": "2026-04-08T19:21:22Z"
}