ClawHub
Back to skill

Security audit

Structured Life Review

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only life-review conversation skill with no code, persistence, tools, credential access, or hidden behavior, though users should treat its emotional-memory prompts with care.

Installers should understand that this skill may guide users into personal and emotional memories. It is appropriate for reminiscence or biography work, but agents should obtain consent, avoid pressure, allow skipping topics, and use stronger emotional-safety guardrails if grief, trauma, loss, or distress appears.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Vague Triggers

Medium
Confidence
92% confidence
Finding
This markdown file describes activation conditions using broad phrases such as 'any form of life review or reminiscence conversation' and 'helping someone explore and articulate memories.' These conditions are not narrowly scoped and do not include exclusion criteria or negative examples, which increases the risk of unintended invocation in general conversation contexts.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The guide encourages autobiographical memory exploration and emotional inquiry, but it does not clearly warn users that recalling personal memories can trigger sadness, grief, trauma, or distress. Although the document later says to stop pushing when a person is distressed, that is not an upfront safety warning or boundary-setting step, so an agent following this guidance may begin potentially sensitive probing without informed consent or a check for readiness.

Scope Creep

Low
Category
Excessive Agency
Content
- Memoir preparation
- Biographical writing support

It is not limited to any one age group, country, or cultural setting. Adjust the
examples, pace, and vocabulary to the person's background.
Confidence
70% confidence
Finding
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Static analysis

No suspicious patterns detected.