ClawHub
Back to skill

Security audit

Spec Coach

Security checks across malware telemetry and agentic risk

Overview

Spec Coach is a single-file instruction skill that interviews users and writes an approved SPEC.md, with no scripts, credentials, network access, or hidden install behavior.

Install this if you want an agent to run a structured specification interview before coding. Before approving the final output, confirm where SPEC.md will be written and whether an existing file could be replaced.

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
88% confidence
Finding
The manifest description contains very broad trigger language such as vague app, feature, workflow, integration, or system idea, plus direct trigger phrases like /spec and /spec-coach. This can cause the skill to activate for many ordinary planning or coding conversations, increasing the chance that users are steered into an unsolicited interview flow or file-writing behavior they did not explicitly request.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill instructs writing SPEC.md to the current working directory after approval, but it does not clearly warn the user that this will modify files or ask for explicit path confirmation. In agent environments, implicit file writes can surprise the user, overwrite an existing SPEC.md, or create artifacts in sensitive or unintended directories.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.