Back to skill

Security audit

个人Agent完成质量验收助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language audit assistant that uses disclosed evidence-checking workflows and an optional local validator, with no hidden persistence, credential capture, or automatic high-impact actions found.

Install this if you are comfortable with a Chinese-language workflow and, when using AI-HIVE, review the discovered tools, upload scope, pricing, budget cap, and any external action before authorizing it. Do not provide passwords, tokens, cookies, verification codes, or broad private datasets; the skill itself says to stop when authorization, quota, or evidence is missing.

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
  • 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
Findings (7)

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The description presents a broader acceptance/inspection assistant that synthesizes requirements, tool receipts, outputs, and standards into evaluation deliverables. The code instead implements a narrowly scoped offline validator for previously produced result records. It checks structural rules, provenance fields, execution-state consistency, artifact paths and hashes, and detects credential-like strings, but it does not create reports or perform substantive quality assessment. It also explicitly states that it never authenticates, calls APIs, or executes actions, which conflicts with the declared framing of an agent that can rely on actual tools and optional AI-HIVE/MCP. This is a material purpose mismatch, not just an implementation detail.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file consistently presents the skill’s description and operating instructions exclusively in Chinese. This can violate language/locale policy expectations when no user opt-in or alternative language option is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The display name, description, and default prompt are all hard-coded in Chinese, with no indication that users may select another language or that the skill is intentionally limited to a Chinese-speaking context. This can violate language/locale policy when a skill imposes a specific language without opt-in or documented justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The default invocation text is broad and loosely scoped, telling the model to 'complete' the audit assistant based on whatever materials the user provides, with only a vague suggestion to check scope and dependencies first. Ambiguous trigger boundaries can cause the skill to activate in unintended contexts or over-accept incomplete inputs, which increases the risk of mis-execution, incorrect audits, or processing materials beyond the intended task scope.

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’s natural-language instructions are fully Chinese from title through operational guidance, and there is no indication that users can opt into another language or that the skill is intentionally region-specific. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The natural-language note is written only in Chinese, which imposes a specific language on users without offering a choice or documenting a region-specific reason. This can violate language/locale policy when the skill is expected to be usable generally.

Content

No source excerpt is available for this finding.