Back to skill

Security audit

UCloud_indeustry_trend

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent research-and-reporting skill for recent industry trend briefs, with no code execution, persistence, credential handling, or hidden data access.

Install this if you want a market-research helper that browses public sources and produces Chinese-first industry briefs. Ask for another language explicitly if needed, and review cited sources because the skill relies on live web research and commercial inference.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · references/funding-and-team-signals.md (reported line 71)May include surrounding context.

md
When relevant, search in both Chinese and English.

## Output Rule

For each industry, add:

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instruction "Write in Chinese unless the user asks otherwise" imposes a default language choice rather than first offering the user a language/locale preference. The policy allows language constraints only when the user opts in or when the constraint is clearly documented and justified as region-specific, which is not stated here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The file requires outputs using Chinese section headers and fallback messages such as 重点融资, 重点团队, and the Chinese no-signal statements. This imposes a specific language on users without any opt-in or alternative, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The template hardcodes section labels and content instructions in Chinese across the main output structure, which effectively imposes a specific language on users. The file does not indicate that Chinese is optional or provide a language choice, so it violates the language/locale policy requirement.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The markdown explicitly directs the operator to search in Chinese and English when relevant, which imposes a language/locale behavior without stating that the user can choose or opt in. Under the policy, forced language behavior can be a natural-language policy violation unless the locale constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.