ClawHub
Back to skill

Security audit

Github Rising Stars

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently runs a local script to query GitHub for fast-growing repositories and does not show hidden persistence, credential use, or unrelated data access.

Before installing, expect the skill to make unauthenticated requests to GitHub and return public repository data. Avoid editing it to add a personal GitHub token unless you understand how that token will be stored and sent.

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 (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill instructs the agent to run a bundled Python script that performs GitHub API queries, but the manifest does not declare any tool scope or allowed-tools boundary for network use. This creates an under-specified privilege surface where the skill can invoke network-capable behavior without explicit least-privilege documentation or enforcement, increasing the chance of unintended external access or policy bypass.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest description says to use the skill when users ask to find 'emerging/rising GitHub projects' or 'discover the hottest new repos in the last 1-7 days,' and also lists generic trigger phrases like 'fast growing repos.' These activation cues are broad and lack clear exclusion conditions, which could cause unintended invocation for general GitHub discovery requests.

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/find_rising.py (reported line 36)May include surrounding context.

python
'order': order,
        'per_page': per_page,
    })
    url = f'https://api.github.com/search/repositories?{params}'
    req = urllib.request.Request(url, headers={
        'Accept': 'application/vnd.github.v3+json',
        'User-Agent': 'github-rising-stars-skill/1.0',

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The trigger list mixes English and Chinese phrases directly in the activation description, but does not explain whether the skill intentionally supports multiple languages or how language selection is handled. This can create an implicit locale/language policy issue because language behavior is prescribed without documented user choice or justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.