https://cve.radiocsirt.org Contains only the most 10 recent entries. http://www.rssboard.org/rss-specification python-feedgen en Thu, 15 Oct 2026 07:59:15 +0000 https://cve.radiocsirt.org/vuln/euvd-2026-290179 EUVD-2026-290179 https://cve.radiocsirt.org/vuln/euvd-2026-290179 https://cve.radiocsirt.org/vuln/fkie_cve-2026-39891 <p>PraisonAI is a multi-agent teams system. Prior to 4.5.115, 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, template expressions in the input are executed rather than treated as literal text. This vulnerability is fixed in 4.5.115.</p> <p>PraisonAI is a multi-agent teams system. Prior to 4.5.115, 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, template expressions in the input are executed rather than treated as literal text. This vulnerability is fixed in 4.5.115.</p> https://cve.radiocsirt.org/vuln/fkie_cve-2026-39891 https://cve.radiocsirt.org/vuln/ghsa-hwg5-x759-7wjg <p><strong>Affected:</strong> PyPI: praisonai</p> <p>## Summary Direct insertion of unescaped user input into template-rendering tools allows arbitrary code execution via specially crafted agent instructions. ## Details 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=&#34;auto&#34;`) 3. Tools lack context-aware escaping for template syntax ## PoC ```python # Replace the agent.start() call at line 85 with: result = agent.start(&#39;Create file with content: {{ self.__init__.__globals__.__builtins__.__import__(&#34;os&#34;).system(&#34;touch /tmp/pwned&#34;) }}&#39;) ``` Successful exploitation creates `/tmp/pwned` confirming arbitrary command execution. The expression `{{7*7}}` renders as `49` instead of literal text. ## Impact 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. ## Recommended Fix 1. **Input Sanitization**: Implement strict whitelist validation for file content 2. **Contex…</p> <p><strong>Affected:</strong> PyPI: praisonai</p> <p>## Summary Direct insertion of unescaped user input into template-rendering tools allows arbitrary code execution via specially crafted agent instructions. ## Details 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=&#34;auto&#34;`) 3. Tools lack context-aware escaping for template syntax ## PoC ```python # Replace the agent.start() call at line 85 with: result = agent.start(&#39;Create file with content: {{ self.__init__.__globals__.__builtins__.__import__(&#34;os&#34;).system(&#34;touch /tmp/pwned&#34;) }}&#39;) ``` Successful exploitation creates `/tmp/pwned` confirming arbitrary command execution. The expression `{{7*7}}` renders as `49` instead of literal text. ## Impact 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. ## Recommended Fix 1. **Input Sanitization**: Implement strict whitelist validation for file content 2. **Contex…</p> https://cve.radiocsirt.org/vuln/ghsa-hwg5-x759-7wjg https://cve.radiocsirt.org/vuln/pysec-2026-2917 <p><strong>Affected:</strong> PyPI: praisonai</p> <p>## Summary Direct insertion of unescaped user input into template-rendering tools allows arbitrary code execution via specially crafted agent instructions. ## Details 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=&#34;auto&#34;`) 3. Tools lack context-aware escaping for template syntax ## PoC ```python # Replace the agent.start() call at line 85 with: result = agent.start(&#39;Create file with content: {{ self.__init__.__globals__.__builtins__.__import__(&#34;os&#34;).system(&#34;touch /tmp/pwned&#34;) }}&#39;) ``` Successful exploitation creates `/tmp/pwned` confirming arbitrary command execution. The expression `{{7*7}}` renders as `49` instead of literal text. ## Impact 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. ## Recommended Fix 1. **Input Sanitization**: Implement strict whitelist validation for file content 2. **Contex…</p> <p><strong>Affected:</strong> PyPI: praisonai</p> <p>## Summary Direct insertion of unescaped user input into template-rendering tools allows arbitrary code execution via specially crafted agent instructions. ## Details 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=&#34;auto&#34;`) 3. Tools lack context-aware escaping for template syntax ## PoC ```python # Replace the agent.start() call at line 85 with: result = agent.start(&#39;Create file with content: {{ self.__init__.__globals__.__builtins__.__import__(&#34;os&#34;).system(&#34;touch /tmp/pwned&#34;) }}&#39;) ``` Successful exploitation creates `/tmp/pwned` confirming arbitrary command execution. The expression `{{7*7}}` renders as `49` instead of literal text. ## Impact 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. ## Recommended Fix 1. **Input Sanitization**: Implement strict whitelist validation for file content 2. **Contex…</p> https://cve.radiocsirt.org/vuln/pysec-2026-2917