ClawHub

Release Prep

Security checks across malware telemetry and agentic risk

Overview

This skill is coherent for release preparation, but it can modify a repository and publish packages with broader triggers and incomplete confirmation safeguards.

Install only if you want an agent to help prepare Python package releases. Use audit mode first, work on a clean branch, review diffs before fixes, and require explicit approval before version bumps, commits, tags, PyPI uploads, or pushing tags. Prefer scoped PyPI tokens and avoid running it on untrusted repositories.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The manifest description includes broad triggers such as "release," "audit code," "check docs," and "publish," which can match many ordinary developer requests and cause the skill to activate outside a narrowly intended context. Because this skill can proceed into fix and release flows that modify files, create tags, and publish artifacts, overly permissive triggering increases the chance of unintended invocation and unsafe repository actions.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill advertises deep analysis near the top, but does not prominently warn that non-audit modes can automatically modify code, documentation, changelogs, versions, tags, and potentially publish packages. That omission is dangerous because users may invoke the skill expecting read-only analysis while the documented workflow includes direct repository mutation and release-side effects.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal