Back to skill

Security audit

Instant Report

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed report-generation skill with no executable payloads, but it may run a heavy Chinese-language workflow even for broad or English report requests.

Install this if you want a structured, Chinese-style industry report workflow that creates Markdown, DOCX, and PDF outputs. Be aware that English requests may still produce Chinese output, and broad research prompts may trigger the full multi-stage report process.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (8)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger description is extremely broad and can activate on many generic research or analysis requests, causing the skill to intercept tasks beyond its intended scope. Over-broad routing can misapply this skill's rigid workflow and output constraints, leading to incorrect behavior, unnecessary subagent delegation, and unintended file-generation actions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill metadata promises automatic language matching for Chinese or English requests, but the researcher subagent is hard-coded to output Chinese. This creates instruction inconsistency that can override user intent, degrade correctness, and cause downstream agents to produce outputs in an unexpected language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The report writer mandates Chinese-only content despite the top-level skill claiming bilingual behavior. This mismatch can cause the final report to violate user requirements and break workflows that depend on English output, especially when the skill is auto-triggered on English prompts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The fact-checker is also forced to respond in Chinese, continuing the language-conflict across the pipeline. In a multi-stage workflow, this inconsistency can make verification output unusable to the caller and can introduce operational errors when later stages expect language alignment with the original request.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The title and opening instruction require reports to prioritize the listed sources, and the first-priority section is explicitly limited to Chinese official data. This creates a natural-language locale policy constraint because it prescribes a specific national/language context without stating that the skill is intended only for China-focused industry reports or allowing user opt-in to another locale.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The file title and all checklist content are written exclusively in Chinese, indicating the skill expects or enforces a specific language/locale. The policy allows locale constraints only when users are given a choice or when the constraint is clearly documented and justified, neither of which appears here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The item '第三人称叙述' requires a fixed narration style as a mandatory language norm. This is a natural-language constraint that may conflict with user preference and is not presented as optional or context-justified.

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 contains natural-language instructions that effectively enforce a specific language/locale for users consuming the skill guidance. The policy allows locale constraints only when users are given an opt-in choice or when the restriction is clearly documented as region-specific and justified, which is not present here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.