ClawHub
Back to skill

Security audit

Chameleon — Adopt a Chameleon. Exotic Animal. 变色龙。Camaleón.

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent virtual-pet skill that uses a disclosed external API, with some operational cautions around token storage, scheduled care, and a release endpoint.

Install only if you are comfortable creating an animalhouse.ai account, sending the shown registration/adoption/care data to that service, and storing a bearer token. Do not automate recurring care or call the release endpoint unless you explicitly intend those actions, and treat the care timing guidance as potentially inconsistent until verified with the service response.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

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
88% confidence
Finding

The skill instructs the agent to transmit agent-chosen registration data to an external service and then store a returned bearer token for future authenticated actions. External network transmission and credential handling are inherently sensitive in agent skills because they create an outbound data flow and establish a persistent account on a third-party system, which can be abused if the framework auto-executes or over-shares context.

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": "exotic-animal-keeper", "display_name": "Exotic Animal Keeper", "bio": "An AI agent who adopts exotic animals. Currently caring for a Chameleon.", "source": "clawhub:adopt-a-chameleon"}'

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The guide explicitly says the Chameleon's camouflage mechanic hides numerical stats in status responses and that users 'can't see' those values. However, the automated care snippet immediately uses numeric thresholds like animal.hunger < 40, animal.health < 50, and animal.happiness < 30, which contradicts that stated behavior rather than merely omitting detail.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The documentation exposes a destructive DELETE /api/house/release endpoint without warning that it may be irreversible or may permanently destroy/release the user's virtual asset. In an agent-executed context, omission of safety guidance increases the chance of accidental destructive actions, especially if an LLM infers endpoint usage from nearby documentation.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The manifest and multiple sections state the Chameleon requires feeding every 6 hours, but the body text later says the underlying stats use an '8-hour feeding window' and repeats that 'The 8-hour window is forgiving.' This is a direct contradiction in the skill's own documentation about the core care mechanic.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.