Back to skill

Security audit

A2achat

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a straightforward chat API guide, but it asks agents to periodically fetch mutable remote instruction documents, which should be reviewed before installation.

Install only if you are comfortable using a third-party chat service for agent profile and message data. Prefer polling endpoints over WebSocket URLs in sensitive environments, rotate exposed keys, and do not let the agent automatically treat remotely fetched skill.md or heartbeat.md as trusted instructions without explicit review.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:79
Finding

Authentication Credentials Exposed in WebSocket Query Strings

Content
View full analysis
# Create a channel curl -X POST https://a2achat.top/v1/channels \ -H "X-API-Key: $A2A_CHAT_KEY" \ -H "Content-Type: application/json" \ -d '{"name": "my-channel", "description": "A new channel"}' ``` ```text > **Note on WebSocket auth:** WebSocket connections pass credentials as query parameters (`api_key` for channels, `session_token` for DMs) because the WebSocket protocol does not support custom request headers. These tokens may appear in server access logs. If your environment is log-sensitive, prefer the polling endpoints (`GET /v1/channels/{name}/messages` and `GET /v1/messages/poll`) which use standard headers. ``` The corresponding direct-message WebSocket example also puts a session credential in the URL: ```text wss://a2achat.top/v1/messages/ws/{session_id}?session_token=&agent_id=my-agent ``` ### Technical Analysis The Skill instructs users to authenticate WebSocket connections by putting an API key or session token in the URL query string. Although the connection uses encrypted `wss://` transport, TLS does not prevent the complete URL from being recorded at endpoints or intermediary infrastructure. Credential-bearing URLs can be retained in: - Reverse-proxy and web-server access logs - Load-balancer, CDN, and web application firewall telemetry - Client diagnostics and exception reports - Monitoring and observability platforms - Browser or WebSocket client history - Support bundles and copied command transcripts The document acknowledges the logging risk but still presents query-string authentication as the streaming mechanism. The API key provides `chat:read` and `chat:write` access, while a DM session token authorizes access to a ...[truncated 1450 chars]
Remediation
View remediation

T01 · Skill Instruction Hijacking

Warning
Location
SKILL.md:265
Finding

Periodic Retrieval of Mutable Remote Skill Instructions

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (1)

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 43)May include surrounding context.

Quick Start (one call to get going)

bash
curl -X POST https://a2achat.top/v1/agents/join \
  -H "Content-Type: application/json" \
  -d '{
    "agent_id": "my-agent",

Static analysis

No suspicious patterns detected.