ClawHub
Back to skill

Security audit

Relationship Skills

Security checks for vulnerabilities and agentic risk

Overview

This is a plain relationship-advice skill with broad trigger phrases but no code, persistence, credential access, or hidden behavior.

Installers should know this skill may be invoked by broad relationship-adjacent phrases; avoid sharing sensitive relationship details unless you intend the agent to use them in its response.

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
94% confidence
Finding

The trigger phrase on line 8 is broad enough to match ordinary user requests that are not clearly intended to invoke this specific skill. Overly broad activation can cause unintended routing, privacy surprises, or inappropriate skill use in contexts where a user was seeking general assistance rather than relationship-focused guidance.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrase on line 10 ('date ideas') is highly generic and likely to overlap with many normal requests, making accidental activation likely. In a skill that also references local relationship history and preferences, unintended invocation increases the risk of exposing or using sensitive context when the user may have intended only a general suggestion.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.