ClawHub
Back to skill

Security audit

GitHub

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed GitHub connector wrapper with real account-changing power, but it labels write/destructive actions and requires user confirmation for them.

Install only if you want agents to operate GitHub through your OOMOL-connected account. Review the GitHub scopes granted in OOMOL, confirm every write or destructive payload before it runs, and avoid pipe-to-shell installation unless you have verified the installer source or used OOMOL's safer official install path.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (2)

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The skill instructs users to install software via a remote script piped directly into a shell (curl ... | bash). This creates a supply-chain and remote code execution risk because whatever is served at that URL executes immediately with the user's privileges, and the skill is a trusted operational document that may normalize unsafe execution.

Content

Scanner excerpt · SKILL.md (reported line 201)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The description says to use this skill for "ANY GitHub request" and "Whenever a task involves GitHub," which is extremely broad and overlaps with many common tasks that merely mention GitHub. The file does not provide exclusions or negative examples to clarify when this skill should not activate, increasing the risk of over-invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.