Unrated

Shell Command Injection in PraisonAI Compute-Bridged File Tools

IdentifiersCVE-2026-57117CWE-78

CVE-2026-57117 is a shell command injection vulnerability in PraisonAI compute-bridged file tooling. The issue affects file operations exposed through read_file, list_files, and write_file when used by LocalManagedAgent or SandboxedAgent with an attached compute provider. Attacker-controlled path arguments are incorporated into shell command execution during compute-bridged file handling, allowing untrusted input to alter the intended command. In the case of write_file, content handling may also be unsafe if treated as shell source rather than inert data. The flaw stems from constructing shell command strings from user-influenced arguments instead of using provider-native file APIs or structured argument passing. Successful exploitation can result in arbitrary command execution in local compute environments or within Docker-backed compute containers.

For your environment

Are you exposed to this one?

Mallory correlates every CVE against your assets, your vendors, and active adversary campaigns. Know which vulnerabilities matter for you, not just which ones are loud.

Start free trial

ANALYST BRIEF

Impact, mitigation & remediation

What it means. What to do now. Patch path, mitigations, and the assume-compromise checklist.

Impact

What an attacker gets, and what they’ve been doing with it.

Successful exploitation allows an attacker who can influence compute-bridged file tool arguments to execute arbitrary shell commands. This can defeat intended least-privilege boundaries and approval assumptions around agent tool use. Where compute is configured as local, the attacker may obtain code execution on the host system. In Docker-backed deployments, the attacker gains code execution inside the container, which may still enable access to sensitive data, tampering with agent workflows, persistence within the execution environment, or further compromise depending on container isolation and mounted resources.

Mitigation

If you can’t patch tonight, do this now.

Until patched, remove read_file, list_files, and write_file from compute_bridged_tools or avoid exposing compute-bridged file tools to untrusted input. Restrict or disable agent interfaces that permit attacker-controlled file path arguments. Maintain strict path validation and workspace boundary enforcement, and avoid shell-backed bridging for file operations until safe provider-native handling is in place.

Remediation

Patch, then assume compromise.

Upgrade PraisonAI to version 4.6.59 or later. Remediation should eliminate shell-string construction for compute-bridged file operations and replace it with provider-native file APIs or structured argument vectors that do not invoke shell interpretation on attacker-controlled input. Ensure write_file content is always handled strictly as data. Add regression coverage for shell metacharacters and other command-injection edge cases across read, list, and write operations.

PUBLIC EXPLOITS

Exploits

No public exploits tracked yet. Mallory keeps watching.

VALID 0 / 0 TOTALView more in app

No public exploit code observed for this vulnerability.

EXPOSURE SURFACE

Affected products & vendors

Products and vendors Mallory has correlated with this vulnerability. Open in Mallory to drill down to specific CPE configurations and version ranges.

VendorProductType

MervinPraisonPraisonaiapplication

Vendor-confirmed product mapping. Mallory continuously reconciles this list against your asset inventory.

ACTIVITY FEED

Recent activity

No public activity tracked yet. Mallory keeps watching.

0 SOURCESView more in app

No public activity observed for this vulnerability.

What this page doesn’t show

The version that knows your environment.

This page is what’s public. Mallory adds the parts that aren’t: which of your assets are affected, which adversaries are exploiting it right now, which detections to deploy, and what to do tonight.

Start free trial

Exposure mapping

Query your assets running an affected version, and investigate the blast radius.

Threat actor evidence

Every observed campaign linking this CVE to a named adversary.

Associated malware

Malware families riding this exploit, with evidence and IOCs.

Detection signatures

YARA, Sigma, Snort, and vendor rules, auto-deployed to your SIEM.

Vendor-by-vendor mapping

Cross-references every affected SKU, including bundled OEM variants.

Social activity