Security audit
MetaInsight Context Engine
Security checks for vulnerabilities and agentic risk
Overview
Prompt-injection indicators were detected in the submitted artifacts (system-prompt-override); human review is required before treating this skill as clean.
Before installing, confirm you are comfortable uploading OpenClaw memory files and referenced documents/images to Tencent Cloud, use least-privilege Tencent credentials, review the default sync settings, and periodically clean local debug files and cloud datasets. ClawScan detected prompt-injection indicators (system-prompt-override), so this skill requires review even though the model response was benign.
SkillSpector was not run because this plugin release contains no bundled skills.
Endor dependency reachability
Checked Nov 7, 2026 · 1:05 AM UTC
2 reachable vulnerabilities
- Medium
garycourt uri-js Mailto Header mailto.ts URI.parse uncaught exception
CVE-2026-1033872 packages import uri-js@4.4.1 directly. See the list of all dependency paths for details. - Medium
tough-cookie Prototype Pollution vulnerability
GHSA-72xf-g2v4-qvf3tough-cookie@2.5.0 is a transitive dependency of metainsight-context-engine@0.1.0 via external direct dependency cos-nodejs-sdk-v5@2.15.4. tough-cookie@2.5.0 is a transitive dependency of cos-nodejs-sdk-v5@2.15.4.
