@rowansenne/docnexus@0.22.1
[English README](./README.md)
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe manifest has no install lifecycle hook, and agent integration requires a selected setup action. The inspected integration adds package-authored project-memory instructions and workspace skill links; it does not establish malicious behavior.
Decision evidence
public snapshot- package.json lists build and prepack scripts but no preinstall, install, or postinstall hook.
- Agent setup is selected through init options or an explicit skills-link command; omitting the init agent option selects no agents.
- Setup links bundled skills and adds a marked project-memory section to CLAUDE.md or AGENTS.md.
- Routine workspace preflight refreshes skills inside the DocNexus workspace; the bundled instructions limit agent writes to drafts and require user agreement before capture.
Source & flagged code
6 flagged · loading sourceManifest-trigger-reachable source writes behavior-bearing configuration into a user or project AI-agent control surface.
dist/src/skills.jsView on unpkgSetup links bundled skills and adds a marked project-memory section to CLAUDE.md or AGENTS.md.
dist/src/skills.jsView on unpkg · L30Findings
Affected versions and remediation
This report applies to @rowansenne/docnexus@0.22.1.
See all versions of @rowansenne/docnexus for other recorded verdicts.
- Review the evidence and your use of @rowansenne/docnexus@0.22.1 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.