Security Digest · Vulnerability record

CVE-2024-6091: AutoGPT bypass of the shell commands denylist settings

A vulnerability in significant-gravitas/autogpt version 0.5.1 allows an attacker to bypass the shell commands denylist settings.

CVSS 9.3 Critical EPSS 0.8% · p57

Should you act?

Critical and remotely reachable

No known exploitation yet, but it is network-reachable without credentials. This signal is computed from CISA KEV, EPSS and CVSS data; it is not an editorial verdict.

  • Not in CISA KEV, but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
  • EPSS 0.8%, percentile 57: FIRST’s model estimates a 0.8% chance of exploitation activity in the next 30 days, higher than 57% of all scored CVEs (moderate). EPSS is a probability, not a verdict.
  • Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
  • Only applies if your dependency tree includes agpt (PyPI) <= 0.5.1, no fixed version listed. Check your lockfile, including transitive dependencies.

What it is

A vulnerability in significant-gravitas/autogpt version 0.5.1 allows an attacker to bypass the shell commands denylist settings. The issue arises when the denylist is configured to block specific commands, such as 'whoami' and '/bin/whoami'. An attacker can circumvent this restriction by executing commands with a modified path, such as '/bin/./whoami', which is not recognized by the denylist.

From the GitHub advisory

A vulnerability in significant-gravitas/autogpt version 0.5.1 allows an attacker to bypass the shell commands denylist settings. The issue arises when the denylist is configured to block specific commands, such as whoami and /bin/whoami. An attacker can circumvent this restriction by executing commands with a modified path, such as /bin/./whoami, which is not recognized by the denylist.

Weakness type: CWE-78.

Product: agpt (PyPI) · Assigned by: @huntr_ai · Published: 2024-09-11

Affected and fixed versions

EcosystemPackageVulnerableFirst fixed
PyPIagpt<= 0.5.1none listed
VendorProductAffected versions (per CVE record)
significant-gravitassignificant-gravitas/autogptunspecified < 0.5.1

Severity scores

Scored byCVSSScoreVector
@huntr_ai3.09.8 CriticalCVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
GitHub4.09.3 CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
  • Attack vector: network (remotely reachable)
  • Attack complexity: low
  • Attack requirements: none
  • Privileges required: none (no login)
  • User interaction: none

CVSS measures how bad a flaw is if exploited, not how likely exploitation is. Read it next to the exploitation data below.

Exploitation and urgency

  • CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
  • CISA SSVC assessment: exploitation poc, automatable yes, technical impact total.
  • FIRST EPSS (model of 2026-10-21): 0.82% probability of exploitation activity in the next 30 days; percentile 57.

Timeline

  • — CVE record last updated
  • — CVE record published by @huntr_ai
  • — GitHub-reviewed advisory GHSA-g84q-54hf-36rg published (critical)

Sources and references

Original sources first. Version and fix details should always be confirmed against the vendor or project advisory.

Vulnerability records

  1. GitHub Advisory GHSA-g84q-54hf-36rg github.com
  2. CVE.org record CVE-2024-6091 cve.org
  3. NVD entry CVE-2024-6091 nvd.nist.gov

Other references from the CVE record and advisory

  1. huntr.com huntr.com
  2. github.com github.com

Critical PyPI advisories · Today’s Security Digest