ClawHub
Back to skill

Security audit

GitHub Repo Analyzer

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a straightforward GitHub repository analyzer that queries public GitHub API data and does not show hidden, persistent, credential-seeking, or destructive behavior.

Reasonable to install if you want public GitHub repository summaries. Be aware that repository names you analyze are sent to GitHub's API, and the advertised issue/PR trend features appear more ambitious than what the bundled script actually implements.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill says 'Get comprehensive repository analysis' and gives a generic usage pattern 'Analyze [repo-url]' without clarifying accepted input formats, boundaries, or non-triggering cases. In a markdown skill description, this can make activation conditions ambiguous because it does not define whether shorthand names, natural-language repo references, or partial URLs should invoke the skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This manifest description says the skill will 'Analyze GitHub repositories' and lists broad capabilities, but it does not specify how or when the skill should be invoked, nor any limiting context or exclusion conditions. For manifest files, missing specificity around trigger scope can cause unintended invocation because common repository-analysis requests may overlap with general user intent.

Content

No source excerpt is available for this finding.