Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
The approval cache in praisonaiagents versions before 4.5.128 records approvals by tool name only, so once a user approves one shell command, later execute_command calls in the same context skip the prompt. An attacker who can drive the LLM agent, for example through prompt injection, could then have it dump process environment variables, including API keys and credentials, into subprocess output. Upgrade praisonaiagents to version 4.5.128 or later.
Not analysed yet
We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.
Severity and exploitation
| Score | Rating | CVSS | Vector | Source |
|---|---|---|---|---|
| 6.8 | Medium | 4.0 | CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N | CNA (VulnCheck) |
- CISA KEV Not listed.
- EPSS 0.0018, the 7th percentile, on 18 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 18 Jun 2026, 22:12 UTC Confirmed by the CVE List
- 31 Oct 2026, 14:07 UTC First seen by agentprime
- 31 Oct 2026, 14:07 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-ffp3-3562-8cv3
- OSV: GHSA-ffp3-3562-8cv3
- github.com/MervinPraison/PraisonAI/security/advisories/GHSA-ffp3-3562-8cv3
- nvd.nist.gov/vuln/detail/CVE-2026-56074
- github.com/MervinPraison/PraisonAI
- github.com/MervinPraison/PraisonAI/releases/tag/v4.5.128
- www.vulncheck.com/advisories/praisonai-tool-approval-cache-bypass-via-coarse-grained-caching
- pypi.org/project/praisonaiagents
- github.com/advisories/GHSA-ffp3-3562-8cv3