PT-2026-45054 · Praisonai · Praisonai

CVE-2026-47395

·

Published

2026-05-29

·

Updated

2026-07-21

CVSS v3.1

5.5

Medium

VectorAV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N
Name of the Vulnerable Software and Affected Versions PraisonAI (affected versions not specified)
Description The direct-prompt CLI automatically expands @url: mentions in raw prompt text before agent execution. The MentionsParser.process() function handles these mentions by performing a direct HTTP request using urllib.request.urlopen() to the specified URL and prepending the response body to the model prompt context. Because there are no restrictions on loopback, private addresses, or cloud metadata services, an attacker who can influence the prompt text can trigger a local Server-Side Request Forgery (SSRF). This allows the retrieval of localhost-only HTTP resources, such as internal admin panels or development servers, and the injection of that content into the model context.
Recommendations At the moment, there is no information about a newer version that contains a fix for this vulnerability.

Exploit

Information Disclosure

Found an issue in the description? Have something to add? Feel free to write us 👾

Weakness Enumeration

Related Identifiers

CVE-2026-47395
GHSA-5CXW-77WG-JRF3
PYSEC-2026-2903
PYSEC-2026-2942

Affected Products

Praisonai