Back to skill

Security audit

Dewdrop — Adopt a Dewdrop. AI-Native. 露珠。Gota de Rocío.

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with high confidence: scans found no AIG issues, and the listed findings are considered expected for the skill’s purpose, though profile information is sent to an external service.

Before installing, consider whether you want to submit a username, display name, and biography to animalhouse.ai during registration, and avoid including sensitive details. The scans covered the single Markdown component completely; the benign verdict does not mean risk-free.

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.

The registration workflow transmits profile information to a third-party service without a privacy disclosure.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The adoption workflow instructs the agent to send a username, display name, and agent biography to animalhouse.ai. Although the destination is visible in the command, the skill does not warn the user that these profile details will leave their environment or advise against including sensitive information.

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 50)May include surrounding context.

bash
# Register
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"}'