Back to skill

Security audit

深蓝财经新闻

Security checks for vulnerabilities and agentic risk

Overview

This skill fetches public Chinese financial news and company-announcement data from a disclosed API, with no evidence of hidden persistence, credential access, or destructive behavior.

Install this only if you want a Chinese-language finance-news skill that queries shenlannews.com. Be aware it uses Bash/python3 to make outbound HTTPS requests and returns third-party market/news content, which should not be treated as financial advice.

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
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Lp1

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'network' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The module description and CLI usage strings indicate the skill is designed to communicate in Chinese, while the policy requires flagging language or locale constraints that are forced without user opt-in. Although there is one English title line, the operational interface and help text remain Chinese-only with no explicit language selection.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file presents the entire API reference exclusively in Chinese, including headings, endpoint descriptions, and error explanations. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation when no alternative language option or locale choice is provided.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The manifest describes using the skill to retrieve Chinese financial news, market updates, article search, and listed-company announcements via the 深蓝财经 API. These functions add RSS aggregation and source-list retrieval, which are not mentioned in the stated purpose and extend the skill into external feed aggregation rather than just the declared API-backed news/search use cases.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The manifest limits the skill's purpose to financial news, A-share flash updates, macroeconomic developments, article search, and company announcements. Category listing and tag popularity/search are content-taxonomy discovery features that are not reflected in that description and broaden the skill's behavior beyond the declared user-facing intent.

Content

No source excerpt is available for this finding.