Back to skill

Security audit

audit-bidding-detection

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language tender-audit workflow that analyzes bidding documents and bidder relationships, with no evidence of hidden execution, persistence, exfiltration, or destructive behavior.

Install this only for authorized procurement or bidding audits. Expect it to process sensitive bidder identities, ownership/personnel links, pricing, document metadata, and audit findings; confirm confidentiality obligations and verify the referenced pipeline/scripts or invoked skills in your environment before running it.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown file describes a full tender-audit workflow involving关联分析, 文件相似度分析, 资质核查, and report generation, which can affect privacy and sensitive organizational data. Under SQP-2 for markdown files, the description should disclose potential data-handling, confidentiality, or system-impact considerations, but no such warning is present in the usage or overview sections.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This manifest contains user-facing names, descriptions, and prompts entirely in Chinese, which effectively forces a specific language for operation. Under the policy, language-specific behavior should either provide user opt-in/choice or clearly document that the skill is intentionally region-specific and why.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. This file presents all instructions and invocation examples only in Chinese, with no user opt-in, alternative language, or justification that the skill is intended solely for a Chinese-language audience.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The skill metadata is entirely presented in Chinese, including the name, description, tags, category, and author-facing labeling, with no indication that users can select another language or that the skill is intended only for a Chinese-language or region-specific audience. Under the policy, forcing a specific language without opt-in or documented justification can be a natural-language policy violation.

Content

No source excerpt is available for this finding.