CVE-2026-57143

LOWCVSS 8.8 · HIGH

Signal is active with 1 mentions in latest observed window

Immediate actions

  • Track advisory updates for patch or workaround availability

Recommended action window: Monitor and triage in normal cycle

NVD description

PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.62, searxng_search and the search_web SearxNG provider pass the LLM-controlled searxng_url parameter directly to requests.get without validating its scheme, host, port, or resolved address. Prompt-injected content can direct the default search tool to internal JSON services, distinguish open and closed internal ports, and attempt cloud-metadata requests, with returned JSON results entering agent context. This issue is fixed in praisonaiagents 1.6.62.

0.0/ 10 priority

Sources & remediation

Weakness type (CWE)
CWE-20CWE-918

Priority

LOW

Exploitation

NONE

PoC

NONE

Patch

NONE

Momentum

NONE

Threat summary

  • 1 mentions across 1 observed day

What's happening

  • 1 total mentions across 1 day

Deep dive

Activity timeline1 mentions / 1d
00111Mentions · 2026-10-16: 110-16
Full discourse1 post
  • Zac Hunsaker@sassafras_ai

    Prompt injection turned PraisonAI's default search tool into an internal network probe. CVE-2026-57143: the model could set the search URL, and the tool fetched it with no host check. Patch to 1.6.78+. Put egress limits on agent tools, not just prompt guardrails.

    4000070
    189 followersView on X

Explore more