registry / @rowansenne/docnexus / 0.20.0
@rowansenne/docnexus@0.20.0
[English README](./README.md)
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe agent configuration writes are scoped to the project and are reached through explicit setup options, while routine skill refreshes stay in the DocNexus workspace. The inspected artifact is packaged data, and no malicious behavior was established.
Static reason
No blocking static signals were detected.
Trigger
A user runs the skills-link command or initializes the project with an agent target.
Impact
The integration makes DocNexus project memory and skills available to the selected agent; no harmful or unconsented behavior was identified.
Mechanism
The CLI links bundled DocNexus skills into project-level agent directories and adds or refreshes a marked DocNexus block in the project instruction file.
AI rationale
The agent configuration writes are scoped to the project and are reached through explicit setup options, while routine skill refreshes stay in the DocNexus workspace. The inspected artifact is packaged data, and no malicious behavior was established.
Evidence
package.jsondist/src/cli.jsdist/src/skills.jsdist/src/agent-context.js
Decision evidence
public snapshotAI called this Clean at 94.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- package.json exposes a CLI and declares no install lifecycle hook.
- Agent setup is initiated through an explicit skills-link command or an init option; init defaults to no agent targets.
- The integration adds a marked project-memory block that points agents to DocNexus recall and says to offer knowledge capture without storing it without user consent.
- Automatic skill refresh copies package skills into the project’s docnexus workspace; agent skill links target project-level agent directories.
- The required offline analysis identifies the flagged artifact as compressed UTF-8 data and reports no analysis limitations.
Evidence against
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetwork
HighEntropyStringsUrlStrings
Source & flagged code
5 flagged · loading sourcedist/src/skills.jsView file
•Manifest-trigger-reachable source links an external AI-agent control path to a behavior-bearing write operation.
import { existssync, readfilesync } from "node:fs";
import { cp, lstat, mkdir, readfile, readlink, rm, stat, symlink, writefile } from "node:fs/promises";
import { installagentcontext } from "./agent-context.js";
import { dirname, join, relative, resolve } from "node:path";
import { fileurltopath } from "node:url";
import { skillspath, workspace_dirname } from "./layout.js";
export const sk[redacted] = ["claude", "codex"];
export const skill_names = [
"docnexus",
"docnexus-extract",
"docnexus-ingest",
"docnexus-recall",
"docnexus-library",
"docnexus-maintain"
];
c
High
Trigger Reachable External Ai Agent Control Surface Mutation
Manifest-trigger-reachable source writes behavior-bearing configuration into a user or project AI-agent control surface.
dist/src/skills.jsView on unpkgdocs/operations/baselines/maintenance-agent-2026-10-17.raw.json.gzView file
•path = [redacted]-agent-2026-10-17.raw.json.gz
kind = high_entropy_blob
sizeBytes = 29679
magicHex = [redacted]
Findings
2 High4 Medium6 Low
HighTrigger Reachable External Ai Agent Control Surface Mutationdist/src/skills.js
HighShips High Entropy Blobdocs/operations/baselines/maintenance-agent-2026-10-17.raw.json.gz
MediumNetwork
MediumEnvironment Vars
MediumShips Compressed Blobdocs/operations/baselines/maintenance-agent-2026-10-17.raw.json.gz
MediumStructural Risk Force Deep Review
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
LowSuspicious Lifecycle Evidencepackage.json
LowAi Review Evidencedist/src/cli.js
Affected versions and remediation
This report applies to @rowansenne/docnexus@0.20.0.
See all versions of @rowansenne/docnexus for other recorded verdicts.
- Review the evidence and your use of @rowansenne/docnexus@0.20.0 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.