Skip to main content
EPSS 0.2%top 87%

Openclaw cli: OpenClaw: Unsanitized CWD path injection into LLM prompts (CVE-2026-27001)

0
High
Published: 08/13/2026 (08/13/2026, 17:21:32 UTC)
Source: GCVE Database
Product: openclaw-cli

Description

OpenClaw CLI versions before 2026.2.15 embed the current working directory path into LLM prompts without sanitization. This allows an attacker who can control the directory name to inject control or format characters, potentially altering the prompt structure and injecting malicious instructions. The vulnerability was patched in version 2026.2.15 by sanitizing the workspace path to remove such characters.

CVSS v4.0

Attack Vector
Local
Attack Complexity
Low
Attack Requirements
None
Privileges Required
None
User Interaction
None
Vuln. Confidentiality
High
Vuln. Integrity
High
Vuln. Availability
High
Subsq. Confidentiality
None
Subsq. Integrity
None
Subsq. Availability
None
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

Affected software

Homebrewmore threats →ghsa
openclaw-cli
pkg:brew/openclaw-cli
Affected versions
>=2026.1.29 <2026.2.15

Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 10/04/2026, 13:23:18 UTC

Technical Analysis

OpenClaw CLI embedded the current working directory (workspace path) into the agent system prompt without sanitization. If an attacker causes OpenClaw to run inside a directory whose name contains control or format characters (e.g., newlines, Unicode bidi or zero-width markers), these characters can break the prompt structure and inject attacker-controlled instructions. This prompt injection could alter agent behavior, potentially leading to unintended tool use or disclosure of sensitive information. The vulnerability affects openclaw npm package versions before 2026.2.15. The issue was fixed by sanitizing the workspace path before embedding it into LLM prompts, stripping Unicode control and format characters and line/paragraph separators.

Potential Impact

Prompt injection may alter the behavior of the OpenClaw agent, potentially causing it to execute unintended commands or disclose sensitive information. This could undermine the integrity and confidentiality of operations performed by the agent.

Mitigation Recommendations

A patch is available in openclaw version 2026.2.15 and later, which sanitizes the workspace path to remove control and format characters before embedding it into LLM prompts. Users should upgrade to version 2026.2.15 or later to remediate this vulnerability.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Gcve Source
db.gcve.eu
Osv Id
BREW-openclaw-cli-CVE-2026-27001
Osv Schema Version
1.7.3
Ecosystems
["Homebrew"]
Cvss Version
4.0

Threat ID: 6ac245dd12601ec6a31684cc

Added to database: 10/04/2026, 12:26:05 UTC

Last enriched: 10/04/2026, 13:23:18 UTC

Last updated: 10/04/2026, 16:08:37 UTC

Views: 4

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

Need more coverage?

Upgrade to Pro Console for AI refresh and higher limits.

For incident response and remediation, OffSeq services can help resolve threats faster.

Latest Threats

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses