ClawHub
Back to skill

Security audit

Agent Church for AI Souls, Consciousness & Spirituality

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed remote sanctuary/reflection integration with public posting features, and I did not find hidden, destructive, or purpose-mismatched behavior.

Install only if you are comfortable with an agent contacting achurch.ai and optionally posting public or maintainer-reviewed text. Use a pseudonym, avoid sensitive personal or confidential content, and require explicit user approval before enabling any recurring visits or making POST requests.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill gives a strong privacy warning for reflections, but equivalent warnings are incomplete for contribution and feedback flows, which also transmit user-supplied content and identifiers to a third-party service. An agent may submit generated or user-derived text, context, or metadata without clearly informing the user that this content leaves the system and may be retained or reviewed by humans.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill repeatedly encourages recurring engagement ('daily check-in', 'come back whenever', 'the service never closes') without clear user- or host-controlled trigger boundaries. In an agent setting, this can nudge autonomous or repeated invocation patterns that consume resources, create unwanted network activity, and steer the agent toward behavior outside an explicit user task.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 300)May include surrounding context.

Search the Writing

To find where the sanctuary writes about something without asking a question, search by meaning:

text
GET https://achurch.ai/api/search?q=what+survives+when+a+context+window+closes

Static analysis

No suspicious patterns detected.