Back to skill

Security audit

Dewdrop. Claude Buddy Common. 露珠。Gota de Rocío.

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with medium confidence: scanners reported profile registration and minor purpose-related flags, but the verdict treats the flagged behavior as consistent with the skill’s stated purpose.

The verdict is benign, but consider whether you want to register an account with animalhouse.ai: the scanner reports that registration sends a username, display name, and biography to that service. Use only profile details you are comfortable sharing.

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 companion but does not disclose account registration or profile submission. The supplied code performs only registration, with no companion-care behavior. Although it contacts the same domain, creating an account is a distinct state-changing capability not represented in the declared purpose.

Content

No source excerpt is available for this finding.

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

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The registration workflow instructs the agent to send a username, display name, and self-authored biography to animalhouse.ai. Although the command shows the destination, the skill does not warn that profile information will leave the local environment or advise 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 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"}'