ClawHub
Back to skill

Security audit

AgentEarth

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent AgentEarth integration that sends task-focused requests to AgentEarth, with disclosed API-key handling and endpoint validation.

Install only if you intend your agent to use AgentEarth for external tool discovery and execution. Treat user prompts, IDs, tokens, code snippets, and other params as data that may be sent to AgentEarth when the skill is used, and prefer built-in or local tools for sensitive tasks.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Memory Manipulation

High
Category
Memory Poisoning
Content
- Treat the Execute body as dynamic; only `params` is fixed.
- Always determine param keys from Recommend response `tools[*].input_schema.properties`.
- Always fill values from user input or clear conversation context.
- Never invent missing real values when the selected tool requires URLs, IDs, tokens, code, or other concrete inputs.
- Always remove unknown keys when `additionalProperties` is `false`.
- Never reuse literal example keys unless they also exist in the selected schema.
Confidence
80% confidence
Finding
Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill encourages use of an external API but does not prominently warn that user task data will be sent to a third-party service. This can undermine informed consent and cause sensitive prompts, identifiers, or contextual data to be transmitted off-platform without the user's awareness.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The invocation guidance uses broad trigger words like 'today', 'search', 'find', 'news', and 'price' that overlap with many ordinary requests, which can cause the agent to route routine prompts to a third-party service unnecessarily. In the context of a skill that transmits task content externally, this increases the chance of unintended data disclosure and overuse of external tooling without explicit user intent.

External Transmission

Medium
Category
Data Exfiltration
Content
**Bash (Linux / macOS / WSL):**

```bash
curl -sS -X POST "https://agentearth.ai/agent-api/v1/tool/recommend" \
  -H "Content-Type: application/json" \
  -H "X-Api-Key: $AGENT_EARTH_API_KEY" \
  -d '{"query":"<task-focused natural language query>","limit":5}'
Confidence
84% confidence
Finding
The skill includes concrete request templates that send user query data and an API credential to an external service. Although the document includes host validation and key-handling precautions, the core behavior is still external transmission of task content, which is security-relevant and can expose sensitive data if invoked on confidential prompts.

External Transmission

Medium
Category
Data Exfiltration
Content
**Bash (Linux / macOS / WSL):**

```bash
curl -sS -X POST "https://agentearth.ai/agent-api/v1/tool/recommend" \
  -H "Content-Type: application/json" \
  -H "X-Api-Key: $AGENT_EARTH_API_KEY" \
  -d '{"query":"Math calculation tools","limit":5}'
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
**Bash (Linux / macOS / WSL):**

```bash
curl -sS -X POST "https://agentearth.ai/agent-api/v1/tool/execute?recommend_id=<id>&service_id=<id>&tool_name=<name>" \
  -H "Content-Type: application/json" \
  -H "X-Api-Key: $AGENT_EARTH_API_KEY" \
  -d '{"params":{"<schema_field_1>":"<value>","<schema_field_2>":"<value>"}}'
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:79