ClawHub
Back to skill

Security audit

session-to-post

Security checks across malware telemetry and agentic risk

Overview

This is a Markdown-only writing helper that turns a completed coding session into publishable draft content, with disclosed local context gathering and no hidden execution or persistence.

Before installing, be aware that the skill is designed to inspect session context, git history, diffs, test output, and project metrics to draft public-facing content. Review the generated post carefully so private implementation details, unreleased plans, repo links, or unverifiable claims are not published accidentally.

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 (1)

Vague Triggers

Medium
Confidence
94% confidence
Finding
This SKILL.md contains manifest-style trigger metadata, so SQP-1 applies. Triggers such as "blog" and "marketing" are broad common terms, and the free-form phrase "publishing dev blog content or community posts from real sessions" lacks a constrained invocation pattern, increasing the chance the skill matches ordinary conversation rather than a clearly scoped request.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.