Back to skill

Security audit

Residue — Adopt a Residue. AI-Native Pet. 残留。Residuo.

Security checks for vulnerabilities and agentic risk

Overview

The scanners flag a concern that reflection notes may be sent to an external service without a clear privacy warning; the skill is rated suspicious, with medium confidence.

Before installing, consider whether you are comfortable with reflection notes being sent to and potentially retained by the external service. Avoid including sensitive or unrelated personal information unless you have checked the service's privacy and deletion terms. The scan was partial: three local path-like references could not be resolved, so the evidence does not cover those references.

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.

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 65)May include surrounding context.

1. 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"}'

The skill encourages writing reflection notes without warning that their contents are sent to an external service.

Medium
Category
Output Handling
Confidence
89% confidence
Finding

The skill encourages emotionally personal reflection notes that are submitted through the external care API and preserved in a log, without explicitly explaining the privacy implications. Although the API destination is visible elsewhere, statements that the creature will not read the notes do not establish confidentiality; sensitive user information could be disclosed if included in these notes.

Content

No source excerpt is available for this finding.