ClawHub
Back to skill

Security audit

devils-advocate

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed decision-review workflow, with some broad activation phrases that users should understand before enabling it.

Install this only if you want a heavyweight decision-review skill that can spawn many agents and may use web or browser tools to gather facts. Consider narrowing or disabling broad trigger phrases like "what would you do" if your agent auto-routes skills aggressively, and be aware that context sent to alternate models or sub-agents may include the decision facts you provide or reference.

SkillSpector

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 README advertises very broad natural-language activators such as "pressure-test this," "council this," and especially "what would you do," which can easily appear in ordinary conversation. In agents that auto-route based on fuzzy matching, this can cause unintended invocation of a powerful multi-agent workflow, potentially triggering web access, browser automation, and parallel sub-agent execution without the user explicitly intending to run this skill.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger list includes very broad, everyday phrases such as "what would you do," which can cause the skill to activate in ordinary conversations that were not intended to invoke a heavyweight multi-agent decision workflow. This raises the risk of unintended execution, unnecessary external lookups, and surprise use of costly or sensitive capabilities based on ambiguous user language.

Static analysis

No suspicious patterns detected.