{"items":[{"id":"NVI-00011966","kind":"vulnerability","title":"PraisonAI: CodeAgent Executes LLM-Generated Code Without Sandboxing and Leaks All Environment Secrets","revision":2,"unknowns":["Customer inventory, deployment, reachability and exploitation have not been inspected.","NVD lastModified does not establish freshness of every associated CPE record."],"lifecycle":"active","identifiers":["GHSA-2xv2-w8cq-5gxw","CVE-2026-61447"],"plain_summary":"GitHub lists this reviewed advisory for praisonaiagents. Published version ranges and source prerequisites are shown below; this is not an inspection of a visitor’s application.","review_status":"source_listed","control_topics":[],"public_actions":[{"summary":"Identify the exact component and deployed version, examine the linked publisher’s conditions, and retain evidence of any mitigation.","source_ids":["sr-34709b7ea8012869d2f8bea2a1117325"],"action_type":"investigate","limitations":"Confirm current vendor support, compatibility and deployment evidence. This report has not tested a fix in your system.","current_supported_target":null}],"schema_version":"1.1.0","source_metrics":[{"kind":"CVSS","as_of":"2026-10-08T16:44:02.000Z","value":"10 critical","meaning":"GitHub source severity; exploitability and local consequence require separate evidence.","source_id":"sr-7207938a444c96d5de1cf28360263605"},{"kind":"CVSS","as_of":"2026-10-25T15:10:00.147Z","value":"10 CRITICAL (3.1)","meaning":"disclosure@vulncheck.com severity; no combined Null risk score.","source_id":"sr-34709b7ea8012869d2f8bea2a1117325"},{"kind":"CVSS","as_of":"2026-10-25T15:10:00.147Z","value":"10 CRITICAL (4.0)","meaning":"disclosure@vulncheck.com severity; no combined Null risk score.","source_id":"sr-34709b7ea8012869d2f8bea2a1117325"}],"why_it_matters":"Published affected context helps an owner decide what evidence to gather. This report has not examined your application.","related_sources":[{"id":"sr-7207938a444c96d5de1cf28360263605","url":"https://github.com/advisories/GHSA-2xv2-w8cq-5gxw","basis":"vendor_advisory","notes":"GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.","title":"GHSA-2xv2-w8cq-5gxw","publisher":"GitHub Advisory Database","observed_at":"2026-11-01T00:58:38.867Z"},{"id":"sr-34709b7ea8012869d2f8bea2a1117325","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-61447","basis":"official_catalog","notes":"This product uses data from the NVD API but is not endorsed or certified by the NVD.","title":"CVE-2026-61447","publisher":"NIST National Vulnerability Database","observed_at":"2026-11-04T02:46:17.217Z"}],"affected_context":[{"certainty":"source_listed","source_ids":["sr-7207938a444c96d5de1cf28360263605"],"technology":"praisonaiagents","known_exclusions":[],"conditions_summary":"### Summary\n`CodeAgent._execute_python()` executes LLM-generated Python code in a subprocess with the complete parent-process environment (`os.environ.copy()`), zero AST validation, zero import restrictions, and no sandbox enforcement — even when `CodeConfig(sandbox=True)` is explicitly set. This allows an attacker who can influence LLM output (via prompt injection in agent input, tool results, or ingested content) to exfiltrate all environment secrets (API keys, database credentials, cloud tokens) and execute arbitrary code on the host.\n\n### Details\n\n`src/praisonai-agents/praisonaiagents/agent/code_agent.py` (lines 253–308):\n\n```python\ndef _execute_python(self, code: str, **kwargs) -> Dict[str, Any]:\n    import subprocess\n    import time\n    import tempfile\n    import os\n\n    start_time = time.time()\n\n    # Write code to temp file\n    with tempfile.NamedTemporaryFile(mode='w', suffix='.py', delete=False) as f:\n        f.write(code)           # ← No AST validation, no import blocking\n        temp_file = f.name\n\n    try:\n        # Execute in subprocess (basic sandboxing)\n        env = os.environ.copy()             # ← FULL parent environment\n        env.update(self._code_config.envi","public_affected_ranges":["<= 1.6.77"]}],"null_published_at":"2026-11-04T10:04:35.930Z","source_updated_at":"2026-10-08T16:44:02.000Z","source_disclosed_at":"2026-10-08T16:44:01.000Z","is_synthetic_fixture":false,"null_last_reviewed_at":null,"public_change_summary":"Source facts changed; compare the preserved prior revision.","null_first_observed_at":"2026-11-01T00:58:38.867Z"},{"id":"NVI-00011966","kind":"vulnerability","title":"PraisonAI: CodeAgent Executes LLM-Generated Code Without Sandboxing and Leaks All Environment Secrets","revision":1,"unknowns":["Customer inventory, deployment, reachability and exploitation have not been inspected."],"lifecycle":"active","identifiers":["GHSA-2xv2-w8cq-5gxw","CVE-2026-61447"],"plain_summary":"GitHub lists this reviewed advisory for praisonaiagents. Published version ranges and source prerequisites are shown below; this is not an inspection of a visitor’s application.","review_status":"source_listed","control_topics":[],"public_actions":[{"summary":"Identify the exact component and deployed version, examine the linked publisher’s conditions, and retain evidence of any mitigation.","source_ids":["sr-7207938a444c96d5de1cf28360263605"],"action_type":"investigate","limitations":"Confirm current vendor support, compatibility and deployment evidence. This report has not tested a fix in your system.","current_supported_target":null}],"schema_version":"1.1.0","source_metrics":[{"kind":"CVSS","as_of":"2026-10-08T16:44:02.000Z","value":"10 critical","meaning":"GitHub source severity; exploitability and local consequence require separate evidence.","source_id":"sr-7207938a444c96d5de1cf28360263605"}],"why_it_matters":"Published affected context helps an owner decide what evidence to gather. This report has not examined your application.","related_sources":[{"id":"sr-7207938a444c96d5de1cf28360263605","url":"https://github.com/advisories/GHSA-2xv2-w8cq-5gxw","basis":"vendor_advisory","notes":"GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.","title":"GHSA-2xv2-w8cq-5gxw","publisher":"GitHub Advisory Database","observed_at":"2026-11-01T00:58:38.867Z"}],"affected_context":[{"certainty":"source_listed","source_ids":["sr-7207938a444c96d5de1cf28360263605"],"technology":"praisonaiagents","known_exclusions":[],"conditions_summary":"### Summary\n`CodeAgent._execute_python()` executes LLM-generated Python code in a subprocess with the complete parent-process environment (`os.environ.copy()`), zero AST validation, zero import restrictions, and no sandbox enforcement — even when `CodeConfig(sandbox=True)` is explicitly set. This allows an attacker who can influence LLM output (via prompt injection in agent input, tool results, or ingested content) to exfiltrate all environment secrets (API keys, database credentials, cloud tokens) and execute arbitrary code on the host.\n\n### Details\n\n`src/praisonai-agents/praisonaiagents/agent/code_agent.py` (lines 253–308):\n\n```python\ndef _execute_python(self, code: str, **kwargs) -> Dict[str, Any]:\n    import subprocess\n    import time\n    import tempfile\n    import os\n\n    start_time = time.time()\n\n    # Write code to temp file\n    with tempfile.NamedTemporaryFile(mode='w', suffix='.py', delete=False) as f:\n        f.write(code)           # ← No AST validation, no import blocking\n        temp_file = f.name\n\n    try:\n        # Execute in subprocess (basic sandboxing)\n        env = os.environ.copy()             # ← FULL parent environment\n        env.update(self._code_config.envi","public_affected_ranges":["<= 1.6.77"]}],"null_published_at":"2026-11-01T01:03:56.618Z","source_updated_at":"2026-10-08T16:44:02.000Z","source_disclosed_at":"2026-10-08T16:44:01.000Z","is_synthetic_fixture":false,"null_last_reviewed_at":null,"public_change_summary":"First indexed by Null; source disclosure date is shown separately.","null_first_observed_at":"2026-11-01T00:58:38.867Z"}],"next_cursor":null,"snapshot_revision":"42594"}