registry / opencode-skills-collection / 4.0.44

opencode-skills-collection@4.0.44

OpenCode CLI plugin that automatically downloads and keeps skills up to date.

AI Security Review

scanned 2mo ago · by lpm-firewall-ai

The package has a real, user-enabled OpenCode control-surface write and ships an explicit code-execution helper, so it warrants a warning. The inspected source does not establish malicious behavior or an unconsented npm lifecycle mutation.

Static reason

One or more suspicious static signals were detected.

Trigger

A user adds the package as an OpenCode plugin and starts OpenCode; the Playwright helper requires explicit execution.

Impact

Bundled third-party instructions become available to the OpenCode agent, and an explicitly invoked helper can execute automation code.

Mechanism

Startup deployment of bundled agent skills and pointer files.

AI rationale

Evidence

package.jsondist/index.jsdist/skill-pointer/index.jsdist/skill-pointer/vault-installer.jsdist/skill-pointer/pointer-generator.jsbundled-skills/playwright-skill/run.jsbundled-skillsskills_index.json~/.config/opencode/skills~/.config/opencode/skill-librariesbundled-skills/playwright-skill/.temp-execution-<timestamp>.js

Decision evidence

public snapshot

AI called this Suspicious at 88.0% confidence as Dangerous Capability with low false-positive risk.

Evidence for warning

The plugin runs whenever OpenCode starts and creates the active OpenCode skills directory.
It copies every indexed bundled skill into the user's OpenCode skill library and writes active pointer skill files.
A bundled Playwright helper can install dependencies and execute JavaScript supplied by its caller.
The package enables a large third-party skill collection by default, creating an agent-extension lifecycle risk.

Evidence against

The manifest has no npm preinstall, install, or postinstall hook; its only lifecycle script is prepublishOnly.
Core plugin code contains no network request, credential collection, shell execution, or remote payload loader.
The Playwright executor is a separately invoked skill helper, not called by the plugin startup path.

Behavioral surface

Source

ChildProcessCryptoDynamicRequireEnvironmentVarsEvalFilesystemNetworkShell

Supply chain

Source & flagged code

8 flagged

bundled-skills/developer-signup-flow/SKILL.mdView file

Lines 145-185markdown

145

146**Good implementation (Stripe):**

1471. OAuth complete

1482. Dashboard shows test API keys immediately

1493. Keys are visible and copyable without extra clicks

1504. "Reveal" pattern for production keys, not test keys

151

152**Bad implementation:**

1531. OAuth complete

1542. "Welcome! Complete your profile to get started"

1553. Profile form required

1564. "Create your first project" wizard

1575. Project settings page

1586. "Generate API key" button

1597. Finally see a key

160

161### Key Display Best Practices

162

163```

164Your API Key

165sk_test_xxxxxxxxxxxxxxxxxxxx [Copy]

High

High Secret

Package contains a high-severity secret pattern.

bundled-skills/developer-signup-flow/SKILL.mdView on unpkg · L165

High

Secret Pattern

Stripe test secret key in bundled-skills/developer-signup-flow/SKILL.md

bundled-skills/developer-signup-flow/SKILL.mdView on unpkg · L165

166

167[Show in cURL example] [Show in SDK example]

168```

169

170- Show key in monospace font

171- Include one-click copy button

172- Show key in context (code example)

173- Test keys visible by default

174- Production keys behind "reveal" click

175- Never require downloading keys to a file

176

177### Multiple Keys and Key Management

178

179Wait until developers need this. First-time signup should show one key.

180

181Introduce key management when:

182- Developer creates a second project

183- Developer invites team members

184- Developer asks about key rotation

185

bundled-skills/playwright-skill/run.jsView file

Lines 1-32javascript

1#!/usr/bin/env node

2/**

3 * Universal Playwright Executor for Claude Code

4 *

5 * Executes Playwright automation code from:

6 * - File path: node run.js script.js

7 * - Inline code: node run.js 'await page.goto("...")'

8 * - Stdin: cat script.js | node run.js

9 *

10 * Ensures proper module resolution by running from skill directory.

bundled-skills/huggingface-tool-builder/references/baseline_hf_api.tsxView file

Lines 19-58tsx

19 Uses HF_TOKEN for auth if the environment variable is set.

21Examples:

22 baseline_hf_api.tsx

23 baseline_hf_api.tsx 5

24 HF_TOKEN=your_token baseline_hf_api.tsx 10

25`);

bundled-skills/gemini-deep-research/scripts/research.pyView file

•path = bundled-skills/gemini-deep-research/scripts/research.py kind = build_helper sizeBytes = 24204 magicHex = [redacted]

Medium

Ships Build Helper

Package ships non-JavaScript build or shell helper files.

bundled-skills/gemini-deep-research/scripts/research.pyView on unpkg

bundled-skills/web-artifacts-builder/scripts/shadcn-components.tar.gzView file

•path = bundled-skills/web-artifacts-builder/scripts/shadcn-components.tar.gz kind = compressed_blob sizeBytes = 19967 magicHex = [redacted]

Medium

Ships Compressed Blob

Package ships compressed or archive-like blobs.

bundled-skills/web-artifacts-builder/scripts/shadcn-components.tar.gzView on unpkg

bundled-skills/theme-factory/theme-showcase.pdfView file

•path = bundled-skills/theme-factory/theme-showcase.pdf kind = high_entropy_blob sizeBytes = 124310 magicHex = [redacted]

High

Ships High Entropy Blob

Package ships high-entropy non-source blobs.

bundled-skills/theme-factory/theme-showcase.pdfView on unpkg

bundled-skills/fedora-hyprland-installer/tests/test-scripts.shView file

•path = bundled-skills/fedora-hyprland-installer/tests/test-scripts.sh kind = payload_in_excluded_dir sizeBytes = 1740 magicHex = [redacted]

High

Payload In Excluded Dir

Package hides binary, compressed, or executable-looking payloads in test/fixture/hidden paths.

bundled-skills/fedora-hyprland-installer/tests/test-scripts.shView on unpkg

Source & flagged code

8 flagged · loading source

bundled-skills/developer-signup-flow/SKILL.mdView file

165patternName = stripe_test_secret severity = high line = 165 matchedText = sk[redacted]]

High

High Secret

Package contains a high-severity secret pattern.

bundled-skills/developer-signup-flow/SKILL.mdView on unpkg · L165

165patternName = stripe_test_secret severity = high line = 165 matchedText = sk[redacted]]

High

Secret Pattern

Stripe test secret key in bundled-skills/developer-signup-flow/SKILL.md

bundled-skills/developer-signup-flow/SKILL.mdView on unpkg · L165

bundled-skills/playwright-skill/run.jsView file

12L13: const fs = require('fs'); L14: const path = require('path');

Medium

Findings

5 High7 Medium6 Low

HighHigh Secretbundled-skills/developer-signup-flow/SKILL.md

HighCredential Exfiltrationbundled-skills/huggingface-tool-builder/references/baseline_hf_api.tsx

HighShips High Entropy Blobbundled-skills/theme-factory/theme-showcase.pdf

HighPayload In Excluded Dirbundled-skills/fedora-hyprland-installer/tests/test-scripts.sh

HighSecret Patternbundled-skills/developer-signup-flow/SKILL.md

MediumDynamic Requirebundled-skills/playwright-skill/run.js

MediumNetwork

MediumEnvironment Vars

MediumShips Build Helperbundled-skills/gemini-deep-research/scripts/research.py

MediumShips Compressed Blobbundled-skills/web-artifacts-builder/scripts/shadcn-components.tar.gz

Medium

Affected versions and remediation

This report applies to opencode-skills-collection@4.0.44.

See all versions of opencode-skills-collection for other recorded verdicts.

Review the evidence and your use of opencode-skills-collection@4.0.44 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: 2026-08-27 05:45:38.077Z (UTC).

Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Affected versions and remediation

Runtime surface

Behavioral surface

Source & flagged code