ClawHub

Github Stars Analyzer

Security checks across malware telemetry and agentic risk

Overview

The skill does what it claims: it fetches a GitHub user's starred repositories and writes a Markdown report, with a caution around optional token handling.

Install only if you want a local GitHub Stars report generator. Prefer running without a token; if rate-limited, use a GitHub token with no permissions and avoid pasting sensitive tokens into shared shells or logs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill instructs the agent to perform network access to the GitHub API and write files to multiple locations, but it does not declare any permissions or capability boundaries. This is dangerous because hidden or undeclared capabilities reduce transparency, bypass least-privilege review, and can lead to unexpected data access or file writes when the skill is invoked.

Credential Access

High
Category
Privilege Escalation
Content
epilog=__doc__,
    )
    parser.add_argument("username", help="GitHub 用户名或主页 URL")
    parser.add_argument("--token", default=None, help="GitHub Personal Access Token（可选）")
    parser.add_argument("--output", default=None, help="输出文件路径（默认：<用户名>_github_stars.md）")
    args = parser.parse_args()
Confidence
89% confidence
Finding
Access Token

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal