EUVD-2026-77177
GHSA-mx9h-pq7w-987x
Severity by source
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
AV:N because the adversary serves malicious content over the network; AC:H for required LocalRuntime mode and successful probabilistic prompt injection; UI:R because the operator must initiate the scan; S:C and C:H/I:H/A:H for full RCE on the operator host outside the agent's scope.
Primary rating from Vendor (VulDB).
CVSS VectorVendor: VulDB
Lifecycle Timeline
4DescriptionCVE.org
A flaw has been found in GH05TCREW PentestAgent up to cf882dabea3ed91cef016cdd115e5426315665a2. This issue affects the function LocalRuntime.execute_command of the file runtime/runtime.py of the component LocalRuntime. Executing a manipulation can lead to os command injection. The attack may be performed from remote. The exploit has been published and may be used. The pull request to fix this issue awaits acceptance.
AnalysisAI
OS command injection via prompt injection in GH05TCREW PentestAgent's LocalRuntime allows a malicious target host to execute arbitrary shell commands on the operator's workstation. When the agent scans an adversary-controlled target, response content such as HTTP bodies, SSH banners, or DNS records flows unfiltered into the LLM's prompt context; a crafted payload steers the LLM into generating reverse-shell or persistence commands that LocalRuntime.execute_command() then runs with full operator-level privileges. …
Unlock full vulnerability intelligence
- Risk assessment & exploitation conditions
- Attack chain visualization
- Remediation with exact patch versions
- Threat intelligence from 22 sources
- Personal watchlist & email alerts
Free forever · No credit card required
Attack ChainAIDerived
Hypothetical attack flow derived from CVE metadata
Vulnerability AssessmentAI
| Exploitation | Exploitation requires three concurrent conditions: (1) the operator must be running PentestAgent with the LocalRuntime backend - users of the --docker Docker runtime are not affected by this path; (2) the agent must be directed to interact with a target whose response content is under adversary control (e.g., an adversary-hosted web application, SSH service, or DNS record set); (3) the adversary's prompt-injection payload embedded in target-controlled output must successfully steer the LLM into emitting a malicious shell command, which is inherently probabilistic. … Additional conditions and limiting factors are described in the full assessment. |
| Risk Assessment | The CVSS 4.0 vector (AV:N/AC:L/AT:N/PR:N/UI:N) overstates exploitability at the metric level, though the resulting score of 6.9 is more defensible than a naive reading of those atomic values would suggest. … Full risk analysis with EPSS, KEV, and SSVC signal comparison available after sign-in. |
| Exploit Scenario | Full exploit scenario with step-by-step reproduction available after sign-in. |
| Remediation | The primary mitigation is to switch to the Docker runtime by invoking PentestAgent with the --docker flag, which confines LLM-generated commands inside a container and prevents prompt-injection payloads from reaching the host shell; this approach is explicitly recommended by the maintainer in the PR #100 description. … Detailed patch versions, workarounds, and compensating controls in full report. |
Threat intelligence, references, and detailed analysis are available after sign-in.
More in Pentestagent
View allSame weakness CWE-78 – OS Command Injection
View allSame technique Command Injection
View allShare
External POC / Exploit Code
Leaving vuln.today