Security audit

Bid Compliance Check

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese bid-compliance checklist assistant that reviews user-provided tender and bid documents without hidden execution, network access, or persistence.

Install only if you want a Chinese-language assistant to review tender and bid documents. Because those documents may contain confidential business, financial, and qualification material, provide only files you are comfortable having the agent analyze in the current workspace.

A.I.G

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

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (3)

Vague Triggers

Medium

Confidence: 87% confidence
Finding: The manifest description embeds multiple trigger words without defining scope, exclusions, or required context, making activation criteria ambiguous. This can cause the system to match loosely related procurement discussions and invoke a skill that expects full tender and bid documents, creating unnecessary exposure of potentially confidential business materials.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger phrases are broad, natural-language requests such as '帮我核对一下标书' and '投标文件检查', which can easily appear in ordinary conversation and may cause the skill to activate when the user did not explicitly intend to invoke it. In a skill that processes sensitive procurement documents, over-broad activation increases the chance of unintended document analysis, data exposure, or workflow hijacking away from the user's actual request.

Natural-Language Policy Violations

Low

Confidence: 96% confidence
Finding: The manifest description is written entirely in Chinese, which imposes a specific language choice in user-facing skill metadata without indicating any language option or opt-in. This can violate language/locale policy when skills are expected to accommodate user preference or explicitly document language constraints.

Static analysis

No suspicious patterns detected.