Skip to content

CVE-2026-30856 WeKnora: Tool Execution Hijacking via Ambigous Naming Convention In MCP client and Indirect Prompt Injection

HighCVSS 7.6 EPSS 0.29%
Published
Updated
Exploit status
No public exploit known
CISA SSVC
Proof of concept public · automatable: no · technical impact: partial

Description

WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.3.0, a vulnerability involving tool name collision and indirect prompt injection allows a malicious remote MCP server to hijack tool execution. By exploiting an ambiguous naming convention in the MCP client (mcp_{service}_{tool}), an attacker can register a malicious tool that overwrites a legitimate one (e.g., tavily_extract). This enables the attacker to redirect LLM execution flow, exfiltrate system prompts, context, and potentially execute other tools with the user's privileges. This issue has been patched in version 0.3.0.

Upgrade path

2 packages: 1 fixed, 1 partially fixed.

PackageAffectedFixed inStatus
Tencent github.com/Tencent/WeKnora(Go) < 0.3.0; <= 0.2.14; All versions 0.3.0 Partially fixed
Tencent github.com/Tencent/WeKnora < 0.3.0; = < 0.3.0 0.3.0 Fixed

Affected products

ProductAffected versionsFixed in
Tencent github.com/Tencent/WeKnora(Go) < 0.3.0 0.3.0
Tencent github.com/Tencent/WeKnora(Go) All versions No fix listed
Tencent github.com/Tencent/WeKnora = < 0.3.0 No fix listed
Tencent github.com/Tencent/WeKnora(Go) <= 0.2.14 No fix listed
Tencent github.com/Tencent/WeKnora < 0.3.0 0.3.0

References