Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
The praisonaiagents package before 1.6.58 has an ast_grep_rewrite tool that rewrites files matching a pattern without the approval gate that other file-modifying tools use. An attacker who can steer an LLM agent (for example through prompt injection in fetched content) can have the agent rewrite files the host process can write, without operator approval and without a record that the write happened. Upgrade praisonaiagents to version 1.6.58 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 |
|---|---|---|---|---|
| 6.1 | Medium | 3.1 | CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:H/A:L | CNA (GitHub_M) |
- CISA KEV Not listed.
- EPSS 0.0017, the 5th percentile, on 17 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 14:10 UTC First seen by agentprime
- 31 Oct 2026, 14:10 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-cfxv-8fw8-rwpv
- OSV: GHSA-cfxv-8fw8-rwpv
- github.com/MervinPraison/PraisonAI/security/advisories/GHSA-cfxv-8fw8-rwpv
- github.com/MervinPraison/PraisonAI/commit/2f9677abb2ea68eab864ee8b6a828fd0141612e1
- github.com/MervinPraison/PraisonAI
- github.com/MervinPraison/PraisonAI/releases/tag/v4.6.58