@rowansenne/docnexus@0.19.0
[English README](./README.md)
AI Security Review
scanned 6d ago · by lpm-firewall-aiThe manifest has no install lifecycle hook, and the flagged agent configuration writes are reachable through explicit CLI actions. Their scope is limited to DocNexus project skills and a marked project instruction block, with guarded cleanup; this supports a clean verdict.
Decision evidence
public snapshot- package.json exposes a CLI and has no preinstall, install, or postinstall hook.
- Agent integration is enabled through the explicit init --agent option or the skills link command.
- Linking creates project-local skill links and adds a marked block to the selected project instruction file.
- The added block directs agents to project memory and says to request consent before storing knowledge.
- Reset requires --force and a DocNexus project marker before removing its workspace and integration files.
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 unpkgLinking creates project-local skill links and adds a marked block to the selected project instruction file.
dist/src/skills.jsView on unpkg · L24Findings
Affected versions and remediation
This report applies to @rowansenne/docnexus@0.19.0.
See all versions of @rowansenne/docnexus for other recorded verdicts.
- Review the evidence and your use of @rowansenne/docnexus@0.19.0 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.