ClawHub
Back to skill

Security audit

Workflow Essentials Free

Security checks for vulnerabilities and agentic risk

Overview

This is mostly a beginner workflow guide, but it grants broad command execution for a narrow educational purpose.

Review this skill before installing. Its content appears educational and not malicious, but it gives the agent command execution authority for a use case that mostly needs explanation and workflow planning. Install only if you are comfortable with that access, and prefer a version that removes exec or limits it to explicit troubleshooting commands requested by the user.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Description-Behavior Mismatch

Medium
Confidence
93% confidence
Finding
The manifest grants `exec` in `allowed-tools` even though the skill is presented as a beginner instructional guide, creating an unnecessary privilege expansion. This increases the risk that an agent could be induced to run shell commands in contexts where users expect only explanatory guidance, especially since the document later references command-line/network checks.

Context-Inappropriate Capability

Medium
Confidence
95% confidence
Finding
The skill explicitly classifies itself as `MD+EXEC` and states that some functionality requires command execution, but the body is primarily educational content about workflow design. This mismatch makes the skill more dangerous because execution capability is not tightly tied to its stated purpose, so an attacker or prompt injection could leverage the extra tool privilege to run unrelated commands.

Vague Triggers

Medium
Confidence
82% confidence
Finding
The activation scope is very broad, with generic phrases around efficiency, automation, batch processing, and workflow optimization, which can cause the skill to trigger in many unrelated contexts. Overbroad triggering is risky because it can insert this skill’s instructions and tool permissions into sessions where they are not needed, increasing the chance of unintended execution or prompt-surface expansion.

Static analysis

No suspicious patterns detected.