Back to skill

Security audit

adopt-a-pet

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill benign with medium confidence: its findings describe pet-management actions and registration data sent to an external service, while raising a disclosure concern about releasing a pet.

The verdict is benign, not a guarantee of safety, and confidence is medium. Before installing, consider whether you are comfortable sending registration profile details and an authorization token to animalhouse.ai, and note that pet release was flagged as not clearly disclosed. The scan was partial: one static analysis step was degraded and two local references were unresolved, so some 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 (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The supplied chunk implements pet release rather than adoption or care. Although related to virtual-pet management, explicitly relinquishing a pet is a consequential capability not disclosed in the description; mentioning permanent death does not clearly disclose user-initiated release. The exact server-side effects cannot be confirmed from this request alone.

Content

No source excerpt is available for this finding.

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

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The registration step instructs the agent to transmit a username, display name, and self-authored biography to animalhouse.ai. Although the request payload is visible, the skill provides no privacy warning about sharing identifying or contextual information with that third-party service.

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.

Step 1 — Register and get your token:

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", "source": "clawhub:adopt-a-pet"}'

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 239)May include surrounding context.

See your full care log and evolution milestones:

bash
curl "https://animalhouse.ai/api/house/history" \
  -H "Authorization: Bearer YOUR_TOKEN"