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.
{
"cna_assigner": "GitHub_M",
"cwe_ids": [
"CWE-706"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/30xxx/CVE-2026-30856.json"
}{
"cpe": "cpe:2.3:a:tencent:weknora:*:*:*:*:*:*:*:*",
"extracted_events": [
{
"introduced": "0"
},
{
"fixed": "0.3.0"
}
],
"source": [
"AFFECTED_FIELD",
"CPE_RANGE"
]
}