@rowansenne/docnexus@0.17.1
[English README](./README.md)
AI Security Review
scanned 7d ago · by lpm-firewall-aiSource inspection found no install lifecycle hook or autonomous agent configuration mutation. Agent integration is project-local and reached through an explicit agent selection or linking command, with the generated instruction requiring consent before storing knowledge.
Decision evidence
public snapshot- The manifest declares a CLI entry point and build, prepack, test, typecheck, audit, and evaluation scripts; no install lifecycle hook appears in the inspected manifest.
- The generated project instruction points agents to DocNexus project memory and says to offer knowledge capture and never store it without the user's consent.
- Agent skills are linked into the project, and the DocNexus instruction block is added by that linking operation.
- The init command defaults to no agent targets unless an agent option is supplied; a separate skills link command performs the linking.
- Automatic skill refresh copies package skills into the project's DocNexus workspace; it does not invoke the agent linking operation.
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 unpkgAgent skills are linked into the project, and the DocNexus instruction block is added by that linking operation.
dist/src/skills.jsView on unpkg · L24Findings
Affected versions and remediation
This report applies to @rowansenne/docnexus@0.17.1.
See all versions of @rowansenne/docnexus for other recorded verdicts.
- Review the evidence and your use of @rowansenne/docnexus@0.17.1 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.