Back to skill

Security audit

新闻联播每日情报分析

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed CCTV Xinwen Lianbo transcript-fetching and report-writing workflow, with ordinary network and file output behavior for that purpose.

Install only if you want a Chinese-language CCTV Xinwen Lianbo reporting workflow. Review broad triggers like “早报,” set the output directory deliberately, and enable scheduled runs or long-term notes only when you want recurring archived reports.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The code is narrowly scoped to retrieval and export of official Xinwen Lianbo text transcripts from tv.cctv.com. That part aligns with the description’s claim of direct official-source scraping via day pages and fallback to index. However, the declared purpose centers on producing an analyzed intelligence report with structured summaries and interpretive sections, while the actual code performs no such analysis—only collection, cleaning, and markdown output. The extra mentions of quick-brief probing and scheduling are also absent from the code chunk. This is therefore a description/behavior mismatch due to significant overstatement of delivered capabilities, even though the fetching portion is accurately represented.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill invokes network access, reads environment-controlled output paths, and writes files, but it declares no explicit tool or permission scope. That creates an unnecessary trust gap: an agent or platform may grant broader capabilities than users expect, enabling unreviewed outbound requests or filesystem writes during routine use.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases are broad enough to activate on common requests like '早报' or general news/report queries, which can cause inappropriate tool invocation. In agent environments, over-broad routing can send unrelated user requests through a networked, file-writing workflow, increasing privacy, cost, and unexpected-behavior risk.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill instructs the agent to persist generated report contents into long-term memory, notes, or files for deduplication without clear minimization or consent boundaries. Persistent storage can retain sensitive user context, create cross-session data leakage, and expose historical outputs beyond the immediate task need.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The entire skill specification, output template, and invocation examples are fixed in Chinese, with no indication that users may choose another language for the report. This can violate language or locale policy when a skill imposes a specific language without user opt-in or documented justification.

Content

No source excerpt is available for this finding.