registry / @agent-native/skills / 0.3.50
@agent-native/skills@0.3.50
Install BuilderIO skills for coding agents.
AI Security Review
scanned 13d ago · by lpm-firewall-aiThe manifest has no install lifecycle hook, and the inspected filesystem, agent configuration, network, and process operations are tied to CLI installation behavior. Telemetry goes to the package's first-party analytics endpoint; no concrete attack behavior was found.
Static reason
No blocking static signals were detected.
Trigger
The user invokes the skills CLI to list or install skills.
Impact
No unintended agent control change, credential transfer, or other attack impact was established.
Mechanism
The CLI copies selected skill files and can register an MCP server for an app-backed skill; device authentication uses a browser approval flow.
AI rationale
The manifest has no install lifecycle hook, and the inspected filesystem, agent configuration, network, and process operations are tied to CLI installation behavior. Telemetry goes to the package's first-party analytics endpoint; no concrete attack behavior was found.
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 lists only build, typecheck, and test scripts; it has no npm lifecycle hook.
- The inspected dependency manifests contain build or test scripts, and their referenced code provides shared exports and prompt UI.
- The CLI calls the installer to copy selected skills; agent configuration writes are tied to selected app skills and can be skipped in a dry run.
- MCP setup writes an entry for the selected server; device authentication displays a browser approval flow before saving a returned token.
- CLI telemetry posts event and install metadata to the package's first-party analytics endpoint.
- The network and child-process calls download a selected GitHub source and extract its archive.
Evidence against
- Network access and child-process execution are present, but the inspected code ties them to source downloads, archive extraction, and first-party CLI telemetry.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetwork
Source & flagged code
5 flaggeddist/index.jsView file
1import { spawnSync } from "node:child_process";
L2: import { randomUUID } from "node:crypto";
High
dist/index.js#virtual:normalized:round1View file
32--force Overwrite a different existing PR Visual Recap workflow
L33: --no-mcp Install skill files only; skip registering the app"s MCP server\n --no-connect Register MCP where possible but skip inline browser/devic...
L34: return file;
High
Same File Env Network Execution
A single source file combines environment access, network access, and code or shell execution; review context before blocking.
dist/index.js#virtual:normalized:round1View on unpkg · L32•stage = ast_semantic_analysis; reason = ast_parse_error; limitedFiles = 1
Findings
4 High2 Medium6 Low
HighChild Processdist/index.js
HighShell
HighSame File Env Network Executiondist/index.js#virtual:normalized:round1
HighSemantic Analysis Limiteddist/index.js#virtual:normalized:round1
MediumNetwork
MediumEnvironment Vars
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
LowSuspicious Lifecycle Evidencepackage.json
LowAi Review Evidencedist/install.js
Affected versions and remediation
This report applies to @agent-native/skills@0.3.50.
See all versions of @agent-native/skills for other recorded verdicts.
- Review the evidence and your use of @agent-native/skills@0.3.50 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.