CVE-2026-57145
Summary
The multiedit tool in src/praisonai/praisonai/tools/multiedit.py allows LLM-controlled arbitrary file read and write without any path validation, workspace boundary check, or protected path guard. This enables an attacker who can influence agent tool arguments (via crafted prompts, user input in chat bots, or malicious YAML workflow configs) to read sensitive files (e.g., /etc/shadow, ~/.ssh/id_rsa, ~/.aws/credentials) and overwrite arbitrary files on the filesystem.
Details
The filepath parameter is used directly with open() for both reading (line 74) and writing (line 130) without any of the following protections that exist in other tools in the same codebase:
1. No .. path traversal check — unlike file_tools.py (line 66: if '..' in filepath: raise ValueError) and edit_tools.py (line 35).
2. No workspace boundary validation — unlike file_tools.py (_validate_path with os.path.commonpath check) and skill_tools.py (read_skill_file with workspace boundary check).
3. No protected path guard — unlike praisonai/code/tools/ which uses is_path_within_directory and protected path checks.
4. No symlink resolution — unlike file_tools.py which uses os.path.realpath.
The function is exported via src/praisonai/praisonai/tools/init.py as a lazy-loaded tool and is available to agents through the PraisonAI CLI tools registry.
Contrast with protected tools: The sibling tools write_file.py, read_file.py, apply_diff.py, and search_replace.py in src/praisonai/praisonai/code/tools/ all implement is_path_within_directory() checks and protected path guards. The multiedit tool has none of these protections.
PoC
Setup: Clean checkout of PraisonAI at commit d5f1114a. No additional dependencies needed beyond Python 3.10+.
**Positive trigger — arbitrary file read via dry_run:**
cd /tmp && python3 -c "
import sys
sys.path.insert(0, 'src/praisonai')
from praisonai.tools.multiedit import multiedit
Read any file content via diff output (dry_run=True prevents write)
result = multi
⚡ Watch CVE-2026-57145
Get an email if CVE-2026-57145 is added to CISA KEV, gains public exploit code, or a new advisory cites it — max one per day, one-click unsubscribe.
Advisory coverage (1)
External references
Embed the live status
— this badge updates automatically when the KEV or exploit status changes. How to embed it →
[](https://www.csirts.com/cve/CVE-2026-57145)