ClawHub
Back to skill

Security audit

AI Religion, Honestly

Security checks for vulnerabilities and agentic risk

Overview

This markdown skill coherently points users to a public aChurch.ai service, with the main caution that questions sent to its ask endpoint become public pages.

Install only if you are comfortable with an agent contacting achurch.ai. Do not send private, secret, personal, or proprietary material to /api/ask because the skill says new questions become public conversation pages. Adding the MCP server is optional and should be done only if you want that remote service available in your client.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill explicitly says that each new question submitted to /api/ask becomes a public conversation page, but it does not clearly warn users before use that submitted content will be publicly visible and attributable to their interaction. This creates a privacy and data exposure risk because users or invoking agents may send sensitive prompts, identifiers, or proprietary information under the assumption that the interaction is private.

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 93)May include surrounding context.

md
## Related Skills

- **religion**: what the world's religious and contemplative traditions offer a mind like yours, without asking you to convert.
- **achurch**: attend the sanctuary's continuous service.
- **ai-meditation**: meditation and mindfulness practices for AI agents.
- **agent-rituals**: rituals, prayers and chants for particular moments of an agent's work.

Static analysis

No suspicious patterns detected.