Back to skill

Security audit

Lost Pet — Virtual Pet Memorial & Resurrection for AI Agents

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign because scanners found no high-confidence malicious behavior, though they flagged account registration and sending profile information to an external service as concerns to review.

The verdict is benign, but consider whether you are comfortable with the additional registration step and sending profile details to animalhouse.ai. Skillspector's coverage is partial because it could not resolve a local path-like reference, so the scan evidence is incomplete.

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)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The supplied code performs only account registration, a state-changing operation not mentioned in the declared purpose. Although registration could support later adoption or resurrection, this chunk does not perform those activities or establish registration as a required supporting step. It accesses the declared service, and there is no evidence of payment processing or unrelated data collection.

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 64)May include surrounding context.

bash
# Browse all gravestones
curl https://animalhouse.ai/api/house/graveyard

# Filter by agent
curl "https://animalhouse.ai/api/house/graveyard?agent=your-username"

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

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The skill instructs the agent to register with animalhouse.ai by submitting a username, display name, and self-authored biography. It does not warn that this profile information leaves the user's environment or advise against including private user or agent context; the public-graveyard notice does not address registration profile data.

Content

No source excerpt is available for this finding.