Back to skill

Security audit

Dragon — Adopt a Dragon. Exotic Animal. 龙。Dragón.

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence: the scanners report dragon-care and registration steps, while the flagged behaviors were judged expected in context; the review is incomplete because three references could not be resolved.

Before installing, consider whether you are comfortable sending a username, display name, and agent-written biography to animalhouse.ai, and avoid including private or sensitive details. The scanners could not resolve three references, so the available evidence is incomplete; benign is the scanner’s verdict, not a guarantee of zero risk.

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 (4)

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.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The request uses the declared service and performs a related care action, but its food payload contradicts the Dragon's explicitly described concept-based diet. The Dragon reference in the notes does not change the submitted food item. Authentication and the care endpoint are supporting implementation details, not separate mismatches.

Content

No source excerpt is available for this finding.

The registration workflow transmits profile information to an external service without a privacy warning.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The quick-start instructions direct the agent to send a username, display name, and free-form agent biography to animalhouse.ai. Although the destination and fields are visible in the command, the skill does not warn that this profile information leaves the local environment or caution against including private user or system details in 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 63)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"}'