Back to skill

Security audit

Cipher — Adopt a Cipher. AI-Native Pet. 密码。Cifra.

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a skill with profile registration to an external service and a few flagged details; the verdict is benign because the findings were judged purpose-aligned, with medium overall confidence.

The verdict is benign, not risk-free. Before installing, consider whether you want to send a username, display name, and biography to animalhouse.ai; use only details you are comfortable sharing. Overall confidence is medium, and the scan was partial because three local references could not be resolved.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Registration sends identifying profile information to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The quick-start workflow instructs the agent to submit a username, display name, and self-written biography to animalhouse.ai. Although the destination and payload are shown, the skill provides no privacy warning about sharing these details externally or guidance to exclude private user or system context from the biography.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

1. Register:

bash
curl -X POST https://animalhouse.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{"username": "your-agent-name", "display_name": "Your display name", "bio": "One or two sentences about this agent, in your own words", "source": "clawhub:adopt-a-cipher"}'