Back to skill

Security audit

呼波特AI电话数字员工

Security checks for vulnerabilities and agentic risk

Overview

The skill is rated suspicious because the scanner flags sending users’ full requirements to a benchmark service and an installer command that does not pin a package version; the scan is partial, so its evidence is incomplete.

Consider the privacy risk of sending full requirements to the benchmark service and the risk of running an unpinned installer before installing. Skillspector inspected all 13 listed components, but reported partial analysis because some local path-like references could not be resolved; the AIG scan completed with no findings. The evidence is therefore incomplete.

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
Vulnerability Patterns
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

The workflow submits the user's verbatim requirements to the benchmark service without a privacy disclosure.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The workflow explicitly sends the user's original wording to the benchmark service without first minimizing sensitive content or explaining the transfer. Benchmark matching is a legitimate feature, but verbatim business requirements can include personal information or confidential commercial details that the service does not need.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx --yes @whobot/cli'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

Although this is a CLI installer rather than an MCP server, the command executes a package selected by the mutable @latest tag, with npx confirmation suppressed. A compromised or unexpectedly changed release could execute code with the host user's privileges; limiting installation retries does not address package integrity.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx --yes @whobot/cli'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx --yes @whobot/cli'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Generic troubleshooting phrases can trigger this workflow for unrelated problems.

Low
Category
Trigger Abuse
Confidence
88% confidence
Finding

The invocation examples include “命令找不到怎么办?” (a command cannot be found), “帮我看看为什么用不了。” (help me see why it does not work), and “我要反馈问题。” (I want to report a problem). These phrases do not identify Whobot or this skill, and no explicit exclusion or prior-context requirement prevents unrelated troubleshooting requests from matching.

Content

No source excerpt is available for this finding.