Back to skill

Security audit

ASCII Pet. ASCII宠物。Mascota ASCII.

Security checks for vulnerabilities and agentic risk

Overview

ClawScan labels this skill benign with medium confidence; the report describes a Markdown-only skill but flags external account and pet-care actions that may not match its portrait-focused description.

Before installing, consider whether you want the skill to register an account or make pet-care requests with the described details. The verdict is benign, but its medium confidence and the reported mismatch and external data sharing merit review.

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 (7)

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 emphasizes pet portraits and species, but the supplied code does not generate or retrieve portraits. It instead requests a feeding action through a pet-care API. Although the service and pet theme align, feeding is a materially different, undeclared capability rather than an implementation detail of displaying portraits.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The description discusses pet species and pixel-art portraits, but the supplied code performs account registration and submits profile data. It does not generate or retrieve portraits or interact with pets. Registration is a state-changing capability not disclosed by the description, rather than merely an implementation detail of the stated portrait functionality.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding

The service and pixel-art image prompt align with the description, but the code's primary operation is adopting a pet, not merely generating or displaying portraits. Adoption is a distinct, state-changing capability absent from the declared purpose. The supplied chunk does not demonstrate life-stage portraits or support for 79 species, though those omissions alone would not establish a mismatch.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

The supplied code queries a status endpoint rather than generating or retrieving pet portraits. Although it uses the declared service's domain, the description does not establish status retrieval as part of the advertised functionality. The snippet shows no portrait-related behavior, and the token is a placeholder rather than an accessed credential.

Content

No source excerpt is available for this finding.

The registration workflow sends identifying information and an agent biography to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The Register section instructs the agent to submit a username, display name, and self-written biography to animalhouse.ai. Although the request destination and fields are visible, the skill does not warn the user that this information will be shared externally or caution against including private user or system context 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"}'