Back to skill

Security audit

新闻联播政策摘要

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently fetches public 新闻联播 text and runs a bundled parser to summarize policy-related items, with no evidence of hidden persistence, credential access, exfiltration, or destructive behavior.

Installers should understand that this skill uses web access to fetch public news pages, writes fetched transcript text to a temporary local file for parsing, runs a bundled Python script, and then deletes that temporary file. Use explicit 新闻联播-related prompts to avoid broad policy questions being routed through this specialized workflow.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (7)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill performs local file write/read operations by saving fetched content to a temporary file and later deleting it, but it does not declare any explicit tool scope or permissions. Missing scope declarations weaken least-privilege controls and can allow the skill to obtain filesystem capabilities without clear review or user awareness.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest description says the skill triggers when users ask about '新闻联播摘要、宏观政策摘报、金融政策风向等', but it does not define clear boundaries for what phrases should or should not invoke the skill. Terms like policy briefings or policy trend questions are broad enough to match ordinary conversation about news or markets, increasing the risk of unintended activation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs the agent to write fetched content to a local path and later delete it without any user-facing notice or consent. Silent filesystem modification is risky because it creates persistent local side effects, may expose sensitive fetched content on disk, and reduces auditability if cleanup fails.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill directs execution of a local Python script via a subprocess without warning the user or constraining execution semantics. Subprocess execution materially increases risk because local scripts can perform arbitrary actions on the host, and the fetched/transcribed content being processed may indirectly influence behavior or output handling.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger "国家政策" is broad and likely to match many generic policy-related user requests beyond the narrow intended scope of CCTV News Broadcast policy extraction. Overbroad activation can cause the skill to be invoked in unrelated contexts, leading to misrouting, unwanted data handling, or policy/financial analysis being presented when the user did not request this specialized workflow.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The manifest description is written entirely in Chinese and describes the skill behavior in a way that implies a fixed Chinese-language workflow, but it does not mention any user language choice or explain that the skill is intentionally locale-specific. Under the policy, forcing a specific language without opt-in can be a natural-language policy concern unless the locale restriction is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code file contains user-facing natural-language documentation entirely in Chinese, and the command-line help and runtime messages are likewise fixed to Chinese. Under the language/locale policy, forcing a specific language without offering user choice can be a policy violation.

Content

No source excerpt is available for this finding.