Security audit

bid-document

Security checks for vulnerabilities and agentic risk

Overview

This is a bid-writing guidance skill with no active code behavior; its main risks are ordinary business-document sensitivity and somewhat broad wording about when to use it.

Install this for procurement or tender-related drafting work. Before using it on real bids, confirm the desired language, review any legal or commercial commitments manually, and provide only the business documents needed for the task.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill metadata says it should be invoked whenever a user needs help writing bids, analyzing tender documents, or performing quality control, but it does not define clear boundaries or exclusions. In an agentic system, overly broad activation conditions can cause the skill to trigger on generic writing or document-analysis requests, leading to inappropriate routing, unnecessary exposure of internal process instructions, or unexpected handling of sensitive procurement content.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The usage guide lists many common assistance scenarios such as document planning, technical writing, quality review, and optimization without limiting them to tender-specific contexts. Because these are common requests across many domains, the skill may be activated too broadly, which increases the chance of misrouting user prompts and applying procurement-specific guidance where it is not appropriate.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: Line L80 instructs the agent to keep document output in a particular商务/权威 style, and the file overall is written as a Chinese-language skill without any opt-in or language-choice guidance. This creates a locale/language policy concern because the skill appears to assume a fixed language/register rather than checking the user's preferred language.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.