Back to skill

Security audit

Fun-ASR speech recognition

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Alibaba DashScope audio transcription helper, with expected cloud API use and no evidence of hidden persistence, deception, or destructive behavior.

Install this only in a virtual environment and use reviewed dependency versions if possible. Treat any submitted audio as being processed by Alibaba Cloud DashScope, and avoid sending confidential, regulated, or consent-sensitive recordings unless that is acceptable for your use case. Consider removing the unnecessary WebSearch permission before use.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (2)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:31
Finding

Unpinned Third-Party Dependencies Create a Supply-Chain Risk

Content
View full analysis
Remediation
View remediation

T05 · Unauthorized Access and Privilege Escalation

Note
Location
.claude/settings.local.json:2
Finding

Unrestricted Web Search Permission Exceeds the Skill's Functional Requirements

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill references use of an environment variable for a cloud API key but does not declare any explicit tool scope or permissions boundary. This creates ambiguity about what capabilities the skill requires and can lead to over-broad execution environments where secret access is not transparently documented or constrained.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill tells users to configure a DashScope API key and use a cloud transcription service, but it does not disclose that uploaded audio will be sent to a third-party provider for processing. Audio may contain sensitive personal, business, or regulated data, so omission of this data-transfer notice can cause unintended privacy and compliance exposure.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The script reads a local audio file and sends its contents to Alibaba Cloud's DashScope ASR service over the network, but this file does not provide a clear user-facing disclosure that audio leaves the local machine. Audio may contain sensitive personal, business, or regulated information, so silent transmission to a third-party service creates a real privacy and data-handling risk even if this is the intended functionality of the skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The script uses Chinese text for the input prompt and file-not-found message, which imposes a specific language on all users. There is no opt-in, locale detection, or documented justification for this constraint in the file.

Content

No source excerpt is available for this finding.