ClawHub
Back to skill

Security audit

Alibaba Cloud AI Audio ASR Realtime

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Alibaba Cloud realtime speech recognition helper with disclosed, limited file output and no evidence of hidden persistence or malicious behavior.

Installers should treat this as a normal provider helper, but avoid saving sensitive audio, transcripts, or credentials in shared workspaces or source control; keep Alibaba Cloud credentials protected and remove debug output when it is no longer needed.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
80% confidence
Finding
The skill performs file-write actions during validation and output collection, but it does not declare any tool scope or permissions boundary. In agent environments, undeclared write capability can lead to unintended filesystem modification and weakens operator visibility into what the skill is allowed to do.

Session Persistence

Medium
Category
Rogue Agent
Content
## Validation

```bash
mkdir -p output/aliyun-qwen-asr-realtime
python -m py_compile skills/ai/audio/aliyun-qwen-asr-realtime/scripts/prepare_realtime_asr_request.py && echo "py_compile_ok" > output/aliyun-qwen-asr-realtime/validate.txt
```
Confidence
60% confidence
Finding
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill instructs users to save session payloads and response samples for a realtime ASR workflow without warning that those artifacts may contain raw audio, transcripts, and other sensitive user content. Persisting such data by default increases the risk of privacy leakage, accidental retention, and exposure through logs or shared workspaces.

Missing User Warnings

Low
Confidence
85% confidence
Finding
The instructions tell users to place an API key in an environment variable or credentials file but provide no guidance on secure secret handling. This can lead to insecure storage, accidental check-in, permissive file permissions, or leakage through shell history and shared environments.

Static analysis

No suspicious patterns detected.