ClawHub
Back to skill

Security audit

Evez Github Manager

Security checks for vulnerabilities and agentic risk

Overview

This GitHub management skill is broadly purpose-aligned, but it advertises high-impact repository actions without clear safety controls or least-privilege guidance.

Install only if you are comfortable letting the agent act on GitHub with the credential you provide. Use a narrowly scoped token for the intended repositories, verify the target repo before any write action, and require explicit confirmation before merges, branch deletion, releases, issue closure, or multi-repo changes.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill declares operational capabilities that can access environment variables and the network, but it does not declare any explicit tool scope such as permissions or allowed-tools. In a GitHub-management skill that uses tokens and performs repository actions, this increases the chance of unintended credential access or unauthorized remote operations because consumers cannot clearly constrain what the skill is allowed to do.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The feature list includes destructive or high-impact actions such as merging PRs, closing issues, deleting branches, and creating releases, but it provides no warning that these actions can modify or permanently affect repositories. In this context, omission of warnings is security-relevant because users may invoke the skill without understanding that it can perform sensitive state-changing operations on live GitHub resources.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This code file performs outbound HTTP requests to the GitHub API and may include the bearer token from GITHUB_TOKEN in the Authorization header, but there is no confirmation prompt, user-facing log, or warning comment/docstring explaining that network transmission occurs. Because this skill sends repository inputs and potentially credentials over the network, it matches the missing user warning criterion for code files.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The authentication section instructs use of GITHUB_TOKEN or an existing integration but does not warn that the skill will act with the privileges of that credential and may perform account or repository actions on the user's behalf. This can lead to overbroad credential use, accidental actions in the wrong repository, or unsafe reuse of highly privileged tokens.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.