ClawHub
Back to skill

Security audit

Github Release Analyzer

Security checks across malware telemetry and agentic risk

Overview

The skill mostly does what it says, but its cron state file path can be redirected outside the intended state folder by a crafted state key.

Manual one-off use for public GitHub releases appears purpose-aligned. For cron use, avoid custom state keys containing slashes, backslashes, '..', or absolute paths until the skill validates state keys and guarantees state files remain inside its own OpenClaw state directory.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill invokes local Python scripts, reads reference files, writes persistent state in cron mode, and likely performs network access to query GitHub releases, yet it declares no permissions. This mismatch is dangerous because it obscures the skill's actual capabilities from reviewers and runtime policy enforcement, increasing the risk of unintended file, environment, or network access without explicit approval.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.