ClawHub
Back to skill

Security audit

fork-it

Security checks for vulnerabilities and agentic risk

Overview

This skill is a GitHub repository search helper whose network and token behavior matches its stated purpose.

Install only if you are comfortable with project search terms and selected repository names being sent to GitHub. If GITHUB_TOKEN is set in the agent environment, the scripts will use it for GitHub API rate limits, so use a least-privilege token or unset it when unnecessary.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 26)May include surrounding context.

md
node scripts/github-search.mjs "keywords" --language js --min-stars 50 --limit 5

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 36)May include surrounding context.

md
node scripts/repo-detail.mjs "owner/repo"

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · references/schema.md (reported line 72)May include surrounding context.

md
Returns detailed repo info (README excerpt, topics, latest release, etc.) as JSON
with `status: "ok"`. On failure: `{"status":"error","code":"...","message":"..."}`.

## Display rules

- `stars: 12300` → "12.3k" (or "1.23万" in Chinese)
- `pushed_days_ago: 3` → "3 days ago" / "3天前"

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill instructs use of shell commands, network access to GitHub, and environment-based authentication via GITHUB_TOKEN, but it declares no explicit tool scope or permissions boundaries. That creates an avoidable over-privilege and transparency problem: an agent may execute external commands or use sensitive environment data without a clear allowlist, increasing the risk of unintended command execution, token exposure, or broader tool access than the task requires.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/github-search.mjs (reported line 9)May include surrounding context.

js
* Uses Node's built-in fetch (no curl / shell dependency, no command injection).
 */

const GITHUB_API = 'https://api.github.com/repos';

function parseArgs() {
  const args = process.argv.slice(2);

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/repo-detail.mjs (reported line 9)May include surrounding context.

js
* Uses Node's built-in fetch (no curl / shell dependency, no command injection).
 */

const GITHUB_API = 'https://api.github.com/repos';

function parseArgs() {
  const args = process.argv.slice(2);

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This code sends the constructed query to the external GitHub Search API via fetch, which transmits user-provided input off-system. Although the file documents that it uses fetch, it does not clearly disclose to the user that their query is sent to GitHub, and there is no confirmation prompt or user-facing notice at runtime.

Content

No source excerpt is available for this finding.