Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
The praisonaiagents PyPI package before 1.5.128 has an arbitrary file read flaw in its read_skill_file tool. The tool accepts any absolute directory as its skill path and skips the workspace boundary check and approval gate that protect comparable tools, so an agent steered by prompt injection could read sensitive files such as credentials or environment variables without an approval prompt. Upgrade to praisonaiagents 1.5.128 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 |
|---|---|---|---|---|
| 6.2 | Medium | 3.1 | CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N | CNA (GitHub_M) |
- CISA KEV Not listed.
- EPSS 0.0035, the 29th percentile, on 18 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 15:02 UTC First seen by agentprime
- 31 Oct 2026, 15:02 UTC Confirmed by OSV