praisonaiagents
Affected
- introduced
0, fixed1.5.115(ecosystem)
Fixed versions
1.5.115
Fix
- Fixed version
1.5.115pip install --upgrade praisonaiagents==1.5.115
Advisory
Also known as: CVE-2026-56078, GHSA-766v-q9x3-g744
PraisonAI has Memory State Leakage and Path Traversal in MultiAgent Context Handling
Summary
The MultiAgentLedger and MultiAgentMonitor components in the provided code exhibit vulnerabilities that can lead to context leakage and arbitrary file operations. Specifically:
MultiAgentLedger uses a dictionary to store ledgers by agent ID without enforcing uniqueness. This allows agents with the same ID to share ledger instances, leading to potential leakage of sensitive context data.MultiAgentMonitor constructs file paths by concatenating the base_path and agent ID without sanitization. This allows an attacker to escape the intended directory using path traversal sequences (e.g., ../), potentially leading to arbitrary file read/write.Details
Vulnerability 1: Memory State Leakage
examples/context/12_multi_agent_context.py:68MultiAgentLedger class uses a dictionary (self.ledgers) to store ledger instances keyed by agent ID. The get_agent_ledger method creates a new ledger only if the agent ID is not present. If two agents are registered with the same ID, they will share the same ledger instance. This violates the isolation policy and can lead to leakage of sensitive context data (system prompts, conversation history) between agents.Vulnerability 2: Path Traversal
examples/context/12_multi_agent_context.py:106MultiAgentMonitor class constructs file paths for agent monitors by directly concatenating the base_path and agent ID. Since the agent ID is not sanitized, an attacker can provide an ID containing path traversal sequences (e.g., ../../malicious). This can result in files being created or read outside the intended directory (base_path).../../etc/passwd) to write or read arbitrary files on the system, potentially leading to information disclosure or file corruption.PoC
Memory State Leakage
multi_ledger = MultiAgentLedger()
# Victim agent (user1) registers and tracks sensitive data
victim_ledger = multi_ledger.get_agent_ledger('user1_agent')
victim_ledger.track_system_prompt("Sensitive system prompt")
victim_ledger.track_history([{"role": "user", "content": "Secret data"}])
# Attacker registers with the same ID
attacker_ledger = multi_ledger.get_agent_ledger('user1_agent')
# Attacker now has access to victim's ledger
print(attacker_ledger.get_ledger().system_prompt) # Outputs: "Sensitive system prompt"
print(attacker_ledger.get_ledger().history) # Outputs: [{'role': 'user', 'content': 'Secret data'}]
Path Traversal
with tempfile.TemporaryDirectory() as tmpdir:
multi_monitor = MultiAgentMonitor(base_path=tmpdir)
# Create agent with malicious ID
malicious_id = '../../malicious'
monitor = multi_monitor.get_agent_monitor(malicious_id)
# The monitor file is created outside the intended base_path
# Example: if tmpdir is '/tmp/safe_dir', the actual path might be '/tmp/malicious'
print(monitor.path) # Outputs: '/tmp/malicious' (or equivalent)
Impact
Recommended Fix
For Memory State Leakage
MultiAgentLedger to throw an exception if an existing agent ID is reused (unless explicitly allowed).For Path Traversal
os.path.join and os.path.realpath to resolve paths, then check that the resolved path starts with the intended base directory.Example fix for MultiAgentMonitor:
import os
def get_agent_monitor(self, agent_id: str):
# Sanitize agent_id to remove path traversal
safe_id = os.path.basename(agent_id.replace('../', '').replace('..\\', ''))
# Alternatively, use a strict allow-list of characters
# Construct path and ensure it's within base_path
agent_path = os.path.join(self.base_path, safe_id)
real_path = os.path.realpath(agent_path)
real_base = os.path.realpath(self.base_path)
if not real_path.startswith(real_base):
raise ValueError(f"Invalid agent ID: {agent_id}")
...
Additionally, consider using a dedicated function for sanitizing filenames.
Medium Basis: CVSS v3 score 6.5, vector CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N
0, fixed 1.5.115 (ecosystem)1.5.115
1.5.115pip install --upgrade praisonaiagents==1.5.115Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.
Check your own computer: guard packages check
Source: PyPA Advisory Database · CC BY 4.0