Back to skill

Security audit

Thornfox. Claude Buddy Uncommon. 荆棘狐。Zorro de Espinas.

Security checks for vulnerabilities and agentic risk

Overview

ClawScan labels this skill benign with medium confidence: the scan completed and found no AIG issues, while Skillspector reported account registration and profile details being sent to an external service.

The verdict is benign, not a guarantee of zero risk. Before installing, consider whether you are comfortable with the reported registration request sending a username, display name, and agent biography to animalhouse.ai. Skillspector reported serializer warnings and an exit status despite recording complete file coverage, so keep that limitation in mind.

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
99% confidence
Finding

The description presents a virtual pet and its gameplay characteristics, whereas the supplied code performs account registration. Although the domain matches, the description does not disclose account creation or profile submission, and the code shows no pet-care behavior. Registration is a distinct capability rather than merely an implementation detail of the described pet mechanics.

Content

No source excerpt is available for this finding.

The registration workflow sends profile information to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The registration instructions transmit a username, display name, and agent biography to animalhouse.ai. The skill does not warn users that these details will leave their environment or advise against including private information in the generated 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 48)May include surrounding context.

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"}'