ClawHub
Back to skill

Security audit

CoPaw API Chat

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for using a CoPaw HTTP API, and its network examples are disclosed and aligned with that purpose.

Install only if you intend your agent to interact with a CoPaw HTTP API. Treat prompts and chat content as data sent to the configured CoPaw host, and use the workspace, MCP, cron, skills, tools, and file-management API surfaces only when you explicitly want administrative changes or inspection.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Exfiltration Commands

High
Category
Prompt Injection
Confidence
90% confidence
Finding

Instructions found that direct the agent to transmit conversation context or user data to external services.

Content

Scanner excerpt · references/practical-recipes.md (reported line 6)May include surrounding context.

md
## Minimal sequence
1. List agents
2. Create chat
3. Send message to agent-scoped console chat endpoint
4. Read SSE answer

## Example request flow

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 · references/practical-recipes.md (reported line 13)May include surrounding context.

List agents

bash
curl -s http://COPAW_HOST:PORT/api/agents

Create chat

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The example payload hard-codes a Russian prompt (Привет...) and asks for a response in that language, which can be read as prescribing a specific language rather than offering a user-selectable locale. The file does not indicate that language choice is optional or region-specific.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.