Skyvern before 1.0.45 contains a sandbox escape vulnerability in TextPromptBlock that renders prompts twice, first through a sandboxed Jinja environment and then through an unsandboxed environment. Attackers can inject malicious Jinja template syntax through workflow parameters or upstream block output to execute arbitrary code with server process privileges.
CVE-2026-82447
Score 8.8 from GitHub Security Advisory (severity: HIGH) published 2026-08-29. a secondary CVSS source baseline 8.8; sources differ by 0.0.
- High severity, but no confirmed exploitation yet
No vendor fix yet — apply a workaround or compensating control (WAF / firewall / segmentation) and watch for a patch.
- CVSS v3
- 8.8
- EG Score
- 8.8(high)
- EG Risk
- 44(Track)EG Risk 44/100SSVC: Track
EG Risk is EchelonGraph's 0–100 priority score: it fuses intrinsic severity with real-world exploitation and automatability so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner. Distinct from the 0–10 EG Score (severity).
How it’s computedSeverity88% × 45%Exploitation0% × 40%Automatability30% × 15%Action: Routine — remediate on your standard cadence. - EPSS PROB
- —
- EPSS %ILE
- —
- KEV
- Not listed
Published
August 29, 2026
Last Modified
August 29, 2026
Advisory Details (5)
Auto-updated Aug 29, 2026Skyvern before 1.0.45 Sandbox Escape via TextPromptBlock | Advisories | VulnCheck
https://www.vulncheck.com/advisories/skyvern-before-1.0.45-sandbox-escape-via-textpromptblockskyvern/skyvern/forge/sdk/prompting.py at v1.0.44 · Skyvern-AI/skyvern · GitHub
https://github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/prompting.pyskyvern/skyvern/forge/sdk/workflow/models/block.py at v1.0.44 · Skyvern-AI/skyvern · GitHub
https://github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/workflow/models/block.pyGitHub - Skyvern-AI/skyvern: Automate browser based workflows with AI · GitHub
https://github.com/Skyvern-AI/skyverncommit d723de621d5b (Skyvern-AI/skyvern)
Fix landed in Skyvern-AI/skyvern commit d723de621d5b — awaiting tagged release
https://github.com/Skyvern-AI/skyvern/commit/d723de621d5b3a340f3cc4d5b46bfe40a9a3124eVendor Advisories for CVE-2026-82447(1)
These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.
Weakness Classification(1)
MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.
Data Freshness Timeline
(refreshed 5× in last 7d / 5× in last 30d)
Each row is a source pipeline that fetched or updated this CVE on that date, with what changed. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. Most recent first.
- 2026-08-30 00:33 UTCEG score recompute
- 2026-08-30 00:33 UTCGHSA enrichment
- 2026-08-29 13:23 UTCEG score recompute
- 2026-08-29 12:24 UTCEG score recompute
- 2026-08-29 12:22 UTCMITRE cvelistV5first tracked
Frequently asked(4)
What is CVE-2026-82447?
When was CVE-2026-82447 disclosed?
What is the CVSS score of CVE-2026-82447?
How do I remediate CVE-2026-82447?
Dependency Blast Radius
Explore the affected products and dependency analysis for CVE-2026-82447
Is Your Infrastructure Affected by CVE-2026-82447?
EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.