Answer in brief
CVE-2024-6091 records a Critical severity (CVSS 9.8) vulnerability in AutoGPT bypass of the shell commands denylist settings. The current sources do not mark it as known exploited. The current feed maps agpt (pip), agpt (pypi). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 9.8. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps agpt (pip), agpt (pypi). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| agptpip | <=0.5.1 | Not reported |
| agptpypi | >=0 | Not reported |
Published upstream
Sep 11, 2024
Evidence: source:ghsa:source_dates:source-dates:recordSource modified
Oct 26, 2026
Evidence: source:ghsa:source_dates:source-dates:recordFirst seen by HOL
Oct 26, 2026
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.
Quoted source text, attributed separately from HOL analysis.