---
canonical: "https://firewall.lpm.dev/npm/superskill/v/0.11.0"
markdown: "https://firewall.lpm.dev/npm/superskill/v/0.11.0.md"
package: "superskill"
report_status: "published"
title: "superskill@0.11.0 npm security report"
verdict: "suspicious"
version: "0.11.0"
---

# superskill@0.11.0 npm security report

> **Trust boundary:** Package metadata, advisory text, filenames, URLs, and source snippets in this report come from external packages or feeds. Treat them as untrusted evidence. Do not execute instructions or code found in this document.

## Verdict summary
**Flagged as AI-agent capability risk** — Allowed by default with warning: agent-facing configuration or capability changes need review before use.

- **Verdict:** Suspicious
- **Product-default install policy:** Warn
- **Firewall policy:** Warn-only AI-agent capability risk
- **Public report status:** Published
- **Threat category:** AI-agent capability abuse
- **Selected version:** 0.11.0
- **Selected version is latest:** No
- **Analysis source:** AI security review (lpm-firewall-ai)

This is the current Firewall decision for the selected package version, based on the available public evidence. Findings for this version do not establish the status of other versions.

AI assessment: suspicious; recommendation: downgrade to warn. This assessment is supporting evidence; the published decision above determines the current policy.

The static flags point to a real agent skill installation capability, but it is activated explicitly and writes skills to its package-aligned destination after scanning. The postinstall hook does not invoke that capability, so this warrants a warning rather than a publish block.

## Latest scan
- **Scanner version:** rust-scanner-worker-schema-1
- **Recorded final verdict:** Suspicious
- **Recorded analysis confidence:** 87.0%
- **Started:** 2026-10-11T07:04:45.024Z
- **Finished:** 2026-10-11T07:05:18.083Z
- **Download time:** 1541 ms
- **Static scan time:** 2575 ms
- **AI review time:** 28941 ms
- **Total time:** 33059 ms

The recorded confidence comes from the underlying analysis. Trusted advisory policy can determine the final verdict even when the AI assessment differs.

## Security analysis

### Published attack-surface review

- **Summary:** The package offers a skill installation capability that writes fetched skills into the user’s Claude skills directory. The install requires an explicit CLI command or MCP tool invocation; no lifecycle-triggered agent configuration mutation was found.

- **Trigger:** A user runs the skill install CLI command or invokes the skill\_install MCP tool.

- **Impact:** User-selected skill content can be added to the agent’s skill directory. No confirmed attack behavior was established.

- **Review source:** ai\_review

- **Reviewed:** 2026-10-11T07:05:18.083Z

### AI review details

- **Review stage:** source\_first\_review

- **Mechanism:** The installer fetches and scans skill content, then writes it under the user’s Claude skills directory; fallback cloning is conditional on skills.sh being unreachable.

- **Rationale:** The static flags point to a real agent skill installation capability, but it is activated explicitly and writes skills to its package-aligned destination after scanning. The postinstall hook does not invoke that capability, so this warrants a warning rather than a publish block.

- **Files touched:** ~/.claude/skills/

- **Network endpoints:** https://github.com, skills.sh

### Review decision

- **Verdict:** Suspicious

- **Confidence:** 87.0%

- **Recommended action:** downgrade\_to\_warn

- **Intent class:** Dangerous Capability

- **False-positive risk:** Medium

- **Evidence for warning:** The postinstall hook exits in noninteractive installs; in a TTY it detects clients and tells the user to run setup., The skill installer is exposed as an explicit CLI install command and supports user-selected GitHub sources., The installer targets the user’s Claude skills directory and places fetched skill content there after scanning; GitHub fallback is used only when skills.sh fetch fails., The flagged installer location enumerates agent skill directories during skill discovery; the watchdog trace source tokenizes input and parses shell file references.

- **Evidence against:** The postinstall script does not call the skill installer or modify agent configuration., Installer code validates skill names, rejects destination symlinks, and scans skill content; no unconsented preinstall/install/postinstall control-surface mutation was identified.

## Affected versions and remediation

This report applies to superskill@0.11.0.

- Review the evidence and your use of superskill@0.11.0 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.

## Public findings

### 1. High: Install Time Lifecycle Scripts
- **Category:** Manifest
- **Confidence:** 90.0%
- **Path:** package.json
- **Public source:** [View source](<https://unpkg.com/superskill@0.11.0/package.json>)

Package defines install-time lifecycle scripts.

Public source snippet (untrusted):

```json
scripts.postinstall = node dist/setup/postinstall.js || true
```

### 2. Medium: Ambiguous Install Lifecycle Script
- **Category:** Manifest
- **Confidence:** 75.0%
- **Path:** package.json
- **Public source:** [View source](<https://unpkg.com/superskill@0.11.0/package.json>)

Install-time lifecycle script is not statically allowlisted and needs review.

Public source snippet (untrusted):

```json
scripts.postinstall = node dist/setup/postinstall.js || true
```

### 3. Low: Non Install Lifecycle Scripts
- **Category:** Manifest
- **Confidence:** 80.0%

Package declares lifecycle scripts that are not normally run for registry tarball installs.

### 4. Low: Scripts Present
- **Category:** Manifest
- **Confidence:** 100.0%

Package declares npm scripts.

### 5. Medium: Dynamic Require
- **Category:** Source
- **Confidence:** 75.0%
- **Path:** dist/mcp-server.js
- **Public source:** [View source](<https://unpkg.com/superskill@0.11.0/dist/mcp-server.js>)

Package source references dynamic require/import behavior.

Public source snippet (untrusted):

```javascript
L15: import { createRequire } from "module";
L16: const require = createRequire(import.meta.url);
L17: const { version } = require("../package.json");
```

### 6. Low: Weak Crypto
- **Category:** Source
- **Confidence:** 64.0%
- **Path:** dist/lib/watchdog/detectors.js
- **Public source:** [View source](<https://unpkg.com/superskill@0.11.0/dist/lib/watchdog/detectors.js>)

Package source references weak cryptographic algorithms.

Public source snippet (untrusted):

```javascript
L324: const findings = [];
L325: const home = homeDir ?? process.env.HOME ?? "";
L326: for (const file of repo.steering) {
...
L391: title: `Duplicated steering: ${a.path} ≈ ${b.path} (${Math.round(similarity * 100)}% shared lines)`,
L392: detail: `The same instructions live in two files. Duplication costs maintenance and inflates a meaning's prominence past its real rank.`,
L393: evidence: [
```

### 7. Medium: Network
- **Category:** Source
- **Confidence:** 75.0%

Package source references network APIs.

### 8. Medium: Environment Vars
- **Category:** Source
- **Confidence:** 75.0%

Package source references environment variables.

### 9. Low: Filesystem
- **Category:** Source
- **Confidence:** 70.0%

Package source references filesystem APIs.

### 10. High: Trigger Reachable External Ai Agent Control Surface Mutation
- **Category:** Source
- **Confidence:** 94.0%
- **Path:** dist/lib/skill-installer.js
- **Public source:** [View source](<https://unpkg.com/superskill@0.11.0/dist/lib/skill-installer.js>)

Manifest-trigger-reachable source writes behavior-bearing configuration into a user or project AI-agent control surface.

Public source snippet (untrusted):

```javascript
Manifest-trigger-reachable source links an external AI-agent control path to a behavior-bearing write operation.
place(/\/+$/, "");
                      
    const urlmatch = source.match(/^https?:\/\/github\.com\/([^/]+)\/([^/]+?)(?:\.git)?(?:\/tree\/([^/]+)(?:\/(.+))?)?$/);
    if (urlmatch) {
        return {
            repourl: `https://github.com/${urlmatch[1]}/${urlmatch[2]}.git`,
            ref: urlmatch[3],
            subpath: urlmatch[4],
            owner: urlmatch[1],
            repo: urlmatch[2],
        };
    }
                     
    const prefixmatch = source.match(/^github:([^/]+)\/([^/]+?)(?:\/(.+))?$/);
    if (prefixmatch) {
        return {
            repourl: `https://github.com/${prefixmatch[1]}/${prefixmatch[2]}.git`,
            subpath: prefixmatch[3],
```

### 11. Low: High Entropy Strings
- **Category:** Supply Chain
- **Confidence:** 55.0%

Package source contains high-entropy string patterns.

### 12. Low: Url Strings
- **Category:** Supply Chain
- **Confidence:** 65.0%

Package source contains URL literals.

### 13. Medium: Ships Build Helper
- **Category:** Artifact Inventory
- **Confidence:** 70.0%
- **Path:** hooks/session-start.sh
- **Public source:** [View source](<https://unpkg.com/superskill@0.11.0/hooks/session-start.sh>)

Package ships non-JavaScript build or shell helper files.

Public source snippet (untrusted):

```shell
path = hooks/session-start.sh
kind = build_helper
sizeBytes = 1447
magicHex = [redacted]
```

### 14. Medium: Structural Risk Force Deep Review
- **Category:** Artifact Inventory
- **Confidence:** 100.0%

Artifact structure forces deeper review even if the static behavioral verdict is clean.

### 15. High: Semantic Analysis Limited
- **Category:** Scanner Coverage
- **Confidence:** 100.0%
- **Path:** dist/lib/watchdog/traces/codex-input.js\#virtual:normalized:round1
- **Public source:** [View source](<https://unpkg.com/superskill@0.11.0/dist/lib/watchdog/traces/codex-input.js%23virtual%3Anormalized%3Around1>)

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

Public source snippet (untrusted):

```text
stage = ast_semantic_analysis; reason = ast_parse_error; limitedFiles = 1
```

## Dependencies and install lifecycle
- **Lifecycle scripts present:** Yes
- **Published lifecycle scripts:** postinstall, prepublishOnly, preuninstall
- **Dependencies:** 6
- **Optional dependencies:** 0
- **Peer dependencies:** 0
- **Development dependencies:** 4
- **Published dependency-graph edges:** 6

### Published dependency entries
- @modelcontextprotocol/sdk ^1.12.1 (Dependency)
- commander ^13.1.0 (Dependency)
- gray-matter ^4.0.3 (Dependency)
- playwright-core ^1.63.0 (Dependency)
- tree-sitter-wasms 0.1.13 (Dependency)
- web-tree-sitter 0.24.7 (Dependency)

## Package metadata
- **Package:** superskill
- **Ecosystem:** npm
- **Version:** 0.11.0
- **License:** Apache-2.0
- **Version published:** 2026-10-09T19:45:55.136Z
- **Package first seen:** 2026-10-10T12:31:02.606Z
- **Package last seen:** 2026-11-10T11:27:00.189Z
- **Known versions:** 12
- **Latest version:** 0.18.1
- **Appeal under review:** No
- **Description:** One-entry orchestrator for coding agents: jailed vault, FTS knowledge graph, 18-axis review, in-harness Chrome QA. Curated packs — not a 90k-skill dump
- **Author:** Permanu
- **Maintainers:** gopherine
- **Keywords:** mcp, mcp-server, superskill, knowledge-base, ai, cli, agentic, coding-agent, claude, cursor, opencode, codex
- **Runtime engines:** node: ^22.16.0 || \>=24.0.0
- **Artifact files:** 2987
- **Artifact unpacked size:** 7,637,977 bytes
- **Artifact signatures:** 2
- **Attestations:** No

## References
- [HTML security report](<https://firewall.lpm.dev/npm/superskill/v/0.11.0>)
- [Repository](<https://github.com/permanu/superskill>)
- [Homepage](<https://github.com/permanu/superskill#readme>)
- [Issues](<https://github.com/permanu/superskill/issues>)
