registry / @agent-native/skills / 0.3.55
@agent-native/skills@0.3.55
Install BuilderIO skills for coding agents.
AI Security Review
scanned 6d ago · by lpm-firewall-aiThe manifest has no install hooks, and the executable runs the CLI only when invoked. Network access, telemetry, and agent configuration writes are tied to CLI operations and match the package's stated skill-installer purpose.
Static reason
No blocking static signals were detected.
Trigger
A user invokes the skills CLI to list or install skills.
Impact
No harmful impact was identified in the reviewed paths.
Mechanism
The CLI may retrieve a selected GitHub source, install skill files, update agent configuration, and send disclosed first-party telemetry.
AI rationale
The manifest has no install hooks, and the executable runs the CLI only when invoked. Network access, telemetry, and agent configuration writes are tied to CLI operations and match the package's stated skill-installer purpose.
Network endpoints2
codeload.github.comanalytics.agent-native.com
Decision evidence
public snapshotAI called this Clean at 95.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The package has no install lifecycle scripts; its npm scripts are build, typecheck, and test.
- The executable calls runSkillsCli with command-line arguments; the exported library entry does not invoke it automatically.
- GitHub source downloads occur inside the CLI flow and fetch from codeload.github.com.
- The CLI describes its first-party analytics telemetry, reported fields, and opt-out settings.
- Skill files and agent configuration are written by installer functions invoked through explicit CLI operations.
Evidence against
- The package includes child-process, network, filesystem, and environment-variable APIs, but the inspected uses serve CLI installation and source retrieval.
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/cli.js
Affected versions and remediation
This report applies to @agent-native/skills@0.3.55.
See all versions of @agent-native/skills for other recorded verdicts.
- Review the evidence and your use of @agent-native/skills@0.3.55 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.