ClawHub

Git Log Intelligence

Security checks across malware telemetry and agentic risk

Overview

This skill is purpose-aligned: it uses a disclosed GitHub token and the GitHub CLI to fetch commit history, then keeps a documented local ignore list for filtering summaries.

Install only if you are comfortable providing a GitHub personal access token to a skill that calls the GitHub CLI. Use the narrowest token scope possible, especially for private repositories, and review the persistent ignore list occasionally so important commits are not hidden by old filters.

SkillSpector

By NVIDIA
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 (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill describes capabilities that include reading environment variables, invoking shell-accessible tooling (`gh`), and persisting data to disk, but it does not declare permissions in a way that clearly constrains or documents those behaviors. This creates a trust and review gap: users or calling agents may invoke a skill with more effective power than is transparently advertised, including access to a GitHub token and durable local state.

Vague Triggers

Medium
Confidence
80% confidence
Finding
The description says to use the skill whenever a user asks broadly about repo changes, changelogs, commits, PRs, or noise filtering, which can cause over-triggering on common requests without confirming scope, repository, or whether persistent state changes are appropriate. In practice this increases the chance of unnecessary token use, unintended access to private repositories, or modification of the ignore list when a simpler non-tool response might suffice.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill supports adding and removing ignore patterns that persist across future runs, but the usage guidance does not require a clear warning or confirmation that these changes are durable. That makes it easy for a transient request to silently alter future summaries, potentially hiding important commits or creating long-term integrity issues in the user's view of repository activity.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal