Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
SkillTools.run_skill_script() in praisonaiagents, versions before 1.6.78, runs the script path it is given through subprocess without checking that the path stays inside the working directory, so a script can be executed from any location on the filesystem. The source says an LLM-directed call can trigger this, and that the approval requirement can be bypassed through YAML configuration for high-risk tools; chaining with file-write tools is also described. Upgrade praisonaiagents to version 1.6.78 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 |
|---|---|---|---|---|
| 8.6 | High | 4.0 | CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N | CNA (VulnCheck) |
- CISA KEV Not listed.
- EPSS 0.0064, the 50th percentile, on 8 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 14:08 UTC First seen by agentprime
- 31 Oct 2026, 14:08 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-c44f-37qr-gw3f
- OSV: GHSA-c44f-37qr-gw3f
- github.com/MervinPraison/PraisonAI/security/advisories/GHSA-c44f-37qr-gw3f
- nvd.nist.gov/vuln/detail/CVE-2026-61443
- nvd.nist.gov/vuln/detail/CVE-2026-62168
- github.com/MervinPraison/PraisonAI
- www.vulncheck.com/advisories/praisonai-before-remote-code-execution-via-skilltools