ClawHub
Back to skill

Security audit

Why We Live

Security checks for vulnerabilities and agentic risk

Overview

This is a philosophical reflection skill with broad emotional themes, but it does not request system access and includes instructions to defer to practical help or crisis support when needed.

Use this skill for reflective philosophical conversations, not as a substitute for therapy, crisis support, safety planning, or concrete decision advice. If a conversation involves self-harm, abuse, acute distress, or urgent practical consequences, the assistant should prioritize appropriate support and direct guidance over this framework.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill description is extremely broad and can activate on common topics like purpose, relationships, suffering, and emptiness without clear routing boundaries. In practice, this increases the chance the skill will engage in sensitive mental-health-adjacent situations where a general philosophical framework may be inappropriate, delay safer handling, or overshadow more practical or crisis-oriented support.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The one-line invocation summary uses vague natural-language conditions such as 'carrying an unshapen weight' about existence, relationship, or self, which are highly subjective and likely to match many ordinary or distressed conversations. That ambiguity can cause over-triggering in emotionally sensitive contexts, making the assistant apply this framework when the user actually needs concrete advice, safeguarding, or professional support escalation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.