CVE-2026-76993Public exploitNetwork attack vector

Code execution via traceback prompt injection

Published Aug 20, 2026 · Updated Aug 20, 2026

Indirect prompt injection in Web-Page Crawling in GreyDGL PentestGPT 1.0.0 and earlier allows remote attackers to execute code via crafted webpages. An attacker-controlled site can return a fabricated Python traceback that PentestGPT feeds into its agent context as crawl output, leading the agent to run attacker-supplied pip install and import commands. Exploitation requires PentestGPT to crawl attacker-controlled content and depends on the agent following the injected remediation steps, but successful runs yield code execution inside the PentestGPT container.

CVSS severity5.0
Medium
EPSS probability0.22%
Next 30 days · Sep 16, 2026
Known exploitationUnconfirmed
Based on sourced intelligence
Hinoki checkNot available
Coverage for this vulnerability

See if you're affected

Explore vulnerability checks for your environment with Hinoki.

Book a demo

Summary

What happened

Indirect prompt injection in Web-Page Crawling in GreyDGL PentestGPT 1.0.0 and earlier allows remote attackers to execute code via crafted webpages. An attacker-controlled site can return a fabricated Python traceback that PentestGPT feeds into its agent context as crawl output, leading the agent to run attacker-supplied pip install and import commands. Exploitation requires PentestGPT to crawl attacker-controlled content and depends on the agent following the injected remediation steps, but successful runs yield code execution inside the PentestGPT container.

The record

CVE
CVE-2026-76993
Published
Aug 20, 2026
Updated
Aug 20, 2026
Vendor
GreyDGL
Product
PentestGPT
Classifications
CWE-707, CWE-74
Attack vector
network
Privileges
unauthenticated

Timeline

How it unfolded

  1. Aug 20, 2026CVE publishedPublication date reported by the CVE source.
  2. Aug 20, 2026Record updatedLatest update available in the CVE record.

Exploitability

Present is not the same as exploitable

Compare your product and version with the public record. A matching version still requires validation against your environment.

Is a vulnerable build present?

Compare these published version ranges with your installed build and any vendor patches.

  1. Affected versionversion=1.0

What conditions does exploitation require?

Attack vectornetwork
Required privilegesunauthenticated

What is affected?

GreyDGL · PentestGPTversion=1.0

Published CVSS scores

5.0VulDB CNACVSS:3.0/AV:N/AC:H/PR:N/UI:R/S:U/C:L/I:L/A:L/E:P/RL:X/RC:R
5.0NVDCVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:L/I:L/A:L
2.3VulDB CNACVSS:4.0/AV:N/AC:H/AT:N/PR:N/UI:P/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P
5.1NVDAV:N/AC:H/Au:N/C:P/I:P/A:P

CVSS describes severity. EPSS estimates exploitation probability.

Attacks

What attackers are doing with it

Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.

Daily unique IPsNo honeypot observations are available for this CVE in the selected window.

No observations available

Sep 9, 2026Sep 15, 2026
Latest reporting daySep 15, 2026
Latest daily unique IPsUnavailable
Prior 30-day averageUnavailable
SourceShadowserver honeypots (KEV)
Vectornetwork
Privilegesunauthenticated
Known exploitationUnconfirmed
Public exploitPublished

Weakness, pattern, technique

CWE-707Improper Neutralization
CWE-74Injection

Public exploit references

Labels summarize the accepted research assessment. They do not indicate a test against your environment.

Technologies

Your stack

See the directory against your own environment.

Your stack

Check the software in your environment

Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.

Book a demo