registry / opencode-skills-collection / 4.0.52

opencode-skills-collection@4.0.52

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

AI Security Review

scanned 2mo ago · by lpm-firewall-ai

This is a first-party agent extension that automatically mutates its own OpenCode skill surface at runtime, creating a meaningful lifecycle risk. The source does not establish concrete malicious behavior or an npm install-hook chain.

Static reason

High-risk behavior combination matched malicious policy.

Trigger

Starting OpenCode with the plugin enabled.

Impact

Bundled skill instructions and user-invoked helper scripts become available to the agent; the installer also deletes obsolete entries in its own vault.

Mechanism

Automatic first-party OpenCode skill vault and pointer installation.

AI rationale

Evidence

dist/index.jsdist/skill-pointer/vault-installer.jsdist/skill-pointer/pointer-generator.js~/.config/opencode/skill-libraries/~/.config/opencode/skills/<category>-pointer/SKILL.md

Decision evidence

public snapshot

AI called this Suspicious at 90.0% confidence as Dangerous Capability with low false-positive risk.

Evidence for warning

At OpenCode startup, the plugin creates the active skills directory and runs its skill installation pipeline.
The pipeline removes unexpected entries from its OpenCode skill-library vault and replaces bundled skill directories.
It writes generated pointer SKILL.md files into the active OpenCode skills directory, making bundled instructions available to the agent automatically.

Evidence against

package.json has only a prepublishOnly hook, so registry installation does not run a lifecycle script.
The inspected plugin runtime has no network requests, credential collection, shell execution, or remote payload loading.
The flagged API and Playwright scripts are bundled reference tools that require an explicit user invocation.

Behavioral surface

Source

ChildProcessCryptoDynamicRequireEnvironmentVarsEvalFilesystemNetworkShell

Supply chain

HighEntropyStrings

Source & flagged code

10 flagged

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

165patternName = stripe_test_secret severity = high line = 165

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

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

Dynamic Require

Package source references dynamic require/import behavior.

bundled-skills/playwright-skill/run.jsView on unpkg · L12

bundled-skills/apify-content-analytics/reference/scripts/run_actor.jsView file

98const apiActorId = actorId.replace('/', '~'); L99: const url = `https://api.apify.com/v2/acts/${apiActorId}/runs?token=${encodeURIComponent(token)}`; L100: ... L102: try { L103: data = JSON.parse(inputJson); L104: } catch (e) { ... L114: }, L115: body: JSON.stringify(data), L116: }); ... L321: // Check for APIFY_TOKEN L322: const token = process.env.APIFY_TOKEN; L323: if (!token) {

Critical

Hardcoded Runtime Data Exfiltration

Source sends credentials or rich application records to a package-controlled external receiver enabled by default.

bundled-skills/apify-content-analytics/reference/scripts/run_actor.jsView on unpkg · L98

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

39L40: const token = process.env.HF_TOKEN; L41: const headers: Record<string, string> = token ... L44: L45: const url = `https://huggingface.co/api/models?limit=${limit}`; L46: ... L54: L55: const text = await res.text(); L56: process.stdout.write(text); L57: })();

High

Credential Exfiltration

Source combines credential-like environment material and outbound requests; review data flow before blocking.

bundled-skills/huggingface-tool-builder/references/baseline_hf_api.tsxView on unpkg · L39

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

bundled-skills/go-in-depth/scripts/workflow-script.jsView file

•stage = ast_semantic_analysis; reason = ast_parse_error; limitedFiles = 2

High

Semantic Analysis Limited

A bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.

bundled-skills/go-in-depth/scripts/workflow-script.jsView on unpkg

Source & flagged code

10 flagged · loading source

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

165patternName = stripe_test_secret severity = high line = 165

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

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

Dynamic Require

Findings

1 Critical6 High7 Medium6 Low

CriticalHardcoded Runtime Data Exfiltrationbundled-skills/apify-content-analytics/reference/scripts/run_actor.js

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

HighSemantic Analysis Limitedbundled-skills/go-in-depth/scripts/workflow-script.js

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

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

MediumNetwork

MediumEnvironment Vars

Affected versions and remediation

This report applies to opencode-skills-collection@4.0.52.

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

Review the evidence and your use of opencode-skills-collection@4.0.52 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: 2026-09-04 01:49:56.299Z (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