Security audit
nexus-agent-framework
Security checks for vulnerabilities and agentic risk
Overview
The skill's files and runtime instructions are coherent with a 'secure agent framework' — it ships documentation and a local security-audit script that inspects and creates local files; it does not request credentials, external installs, or network access.
This package appears coherent and contains only docs plus a local audit script. Before running: 1) Inspect scripts/security-audit.sh yourself (it only greps, checks permissions, creates memory/ subdirectories, and reports), 2) Run the audit in a safe working directory (not as root) or in a sandbox to avoid unexpected file writes, 3) Review WAL.md retention rules and any files the framework will create to ensure you are comfortable with local retention policies (some docs mention permanent retention for high-severity logs), and 4) If you plan to let an agent run this autonomously, confirm its trust level/settings so it doesn't run commands in sensitive locations. If you want extra assurance, run the audit with --skip-network and -q for a conservative check and manually verify any warnings reported.
SkillSpector findings are pending for this release.
