registry / @agent-native/skills / 0.3.51
@agent-native/skills@0.3.51
Install BuilderIO skills for coding agents.
AI Security Review
scanned 12d ago · by lpm-firewall-aiSource inspection found no npm lifecycle hook or concrete attack behavior. Agent configuration writes are part of the user-invoked CLI flow, and the inspected dependencies show no install lifecycle scripts.
Static reason
No blocking static signals were detected.
Trigger
A user runs a CLI command such as list or add.
Impact
No malicious or unconsented attack impact was established.
Mechanism
The CLI processes the requested skill operation and can register MCP settings through an interactive authentication flow.
AI rationale
Source inspection found no npm lifecycle hook or concrete attack behavior. Agent configuration writes are part of the user-invoked CLI flow, and the inspected dependencies show no install lifecycle scripts.
Decision evidence
public snapshotAI called this Clean at 92.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- package.json exposes the CLI and lists only build, typecheck, and test scripts; it has no install lifecycle hook.
- The installer resolves a supplied source and selected skills; managed instruction-file writes occur through that installer.
- MCP configuration is written through an atomic file writer. The CLI initiates registration, and bearer-token setup requires an interactive flow against a hosted URL.
- The inspected dependency manifests list build and test scripts only; their inspected entrypoints are a shared export barrel and a prompt library.
- Telemetry is started by CLI commands, targets the package's first-party analytics service, and supports opt-out through environment settings.
Evidence against
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetworkShell
HighEntropyStringsUrlStrings
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@0.3.51.
See all versions of @agent-native/skills for other recorded verdicts.
- Review the evidence and your use of @agent-native/skills@0.3.51 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.