ClawHub
Back to skill

Security audit

GitHub AI Trends Reporter

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently fetches public GitHub repository trend data and formats it, with no hidden persistence or unrelated data access found.

Install only if you are comfortable with the skill making live requests to api.github.com. If you provide a GitHub token or have GITHUB_TOKEN in the environment, use a low-privilege token because the script will send it to GitHub for rate limiting.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (5)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill instructs the agent to run a local Python script that uses network access and may consume a GitHub token from arguments or the environment, but the manifest declares no explicit tool scope or permission boundaries. This creates an authorization gap: an agent may invoke code, make outbound requests, and access environment secrets without those capabilities being clearly constrained or auditable at the skill level.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description contains broad trigger phrases such as requests about AI trends, GitHub trending, leaderboards, or popular AI repos, which can cause the skill to activate for common user intents without strong specificity. In context, that over-broad matching is less about direct exploitation and more about unintended invocation of a networked/code-executing skill, increasing the chance of unnecessary external calls or token use.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The period labels are hard-coded in Chinese ("日榜", "周榜", "月榜"), which contributes to producing non-optional Chinese-language output. This is a natural-language policy issue because the script does not offer a language choice or explain why a Chinese-only locale is required.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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/fetch_trends.py (reported line 21)May include surrounding context.

python
params = urllib.parse.urlencode({
        "q": query, "sort": sort, "order": order, "per_page": per_page
    })
    url = f"https://api.github.com/search/repositories?{params}"
    headers = {"Accept": "application/vnd.github+json", "User-Agent": "github-ai-trends"}
    if token:
        headers["Authorization"] = f"Bearer {token}"

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The generated heading and timestamp label (for example, "GitHub AI 趋势榜" and "生成时间") are fixed in Chinese. Because the file provides no locale selection or user opt-in, it violates the language/locale policy criteria for natural-language content.

Content

No source excerpt is available for this finding.