registry / @rowansenne/docnexus / 0.17.0
@rowansenne/docnexus@0.17.0
[English README](./README.md)
AI Security Review
scanned 7d ago · by lpm-firewall-aiThe manifest has no install lifecycle hook, and the agent configuration writes are reachable through explicit setup commands. The inspected behavior installs first-party DocNexus project-memory guidance and skills, with user consent required before memory capture.
Static reason
No blocking static signals were detected.
Trigger
A user runs `docnexus skills link --target ...` or selects an agent with `docnexus init --agent ...`.
Impact
No malicious impact was established; the behavior sets up the package's project-memory feature for the selected agent.
Mechanism
The command links packaged DocNexus skills into the project's agent skills directory and adds DocNexus project-memory guidance to CLAUDE.md or AGENTS.md.
AI rationale
The manifest has no install lifecycle hook, and the agent configuration writes are reachable through explicit setup commands. The inspected behavior installs first-party DocNexus project-memory guidance and skills, with user consent required before memory capture.
Evidence
CLAUDE.mdAGENTS.md.agents/skills.claude/skillsdocnexus/skills
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 lists build, prepack, test, typecheck and evaluation scripts; it has no preinstall, install or postinstall hook.
- The agent-context code targets CLAUDE.md or AGENTS.md and adds a marked DocNexus project-memory block.
- That block directs agents to offer memory capture and says not to store it without user consent.
- The skills code places selected agent links in the project's .agents/skills or .claude/skills directory and links DocNexus skills.
- The CLI exposes linking through an explicit skills link command or optional init --agent selection.
Evidence against
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetwork
HighEntropyStringsUrlStrings
Source & flagged code
6 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 unpkgpackage.jsonView file
36"scripts": {
"build": "node -e \"require('node:fs').rmSync('dist', { recursive: true, force: true })\" && tsc -p tsconfig.json && node -e \"require('node:fs').chmodSync('dist/src/cli.js', 0o755)\"",
"prepack": "npm run build",
"test": "vitest run",
"typecheck": "tsc -p tsconfig.json --noEmit",
"audit:prod": "npm audit --omit=dev --audit-level=high",
"eval:retrieval": "npm run build && node scripts/eval-retrieval.mjs",
"eval:retrieval:quality": "npm run build && node scripts/eval-retrieval-quality.mjs",
"eval:knowledge": "npm run build && node scripts/eval-knowle
Findings
1 High2 Medium9 Low
HighTrigger Reachable External Ai Agent Control Surface Mutationdist/src/skills.js
MediumNetwork
MediumEnvironment Vars
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
LowSuspicious Lifecycle Evidencepackage.json
LowSuspicious Lifecycle Evidencepackage.json
LowAi Review Evidencedist/src/agent-context.js
LowAi Review Evidencedist/src/agent-context.js
LowAi Review Evidencedist/src/agent-context.js
Affected versions and remediation
This report applies to @rowansenne/docnexus@0.17.0.
See all versions of @rowansenne/docnexus for other recorded verdicts.
- Review the evidence and your use of @rowansenne/docnexus@0.17.0 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.