Security audit

标书自用调整

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed bid-writing guidance skill with no code execution, persistence, credential access, or hidden data movement found.

Appropriate to install for bid-document drafting and review. Before relying on it for a real submission, verify all qualifications, pricing, legal compliance, and commitments with responsible business/legal reviewers, and avoid providing confidential tender or company materials unless your environment is approved for that data.

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: 93% confidence
Finding: The front-matter description says the skill should be invoked whenever a user needs bid writing, tender analysis, or quality control, but it does not define exclusion criteria or boundaries against adjacent domains such as legal advice, procurement compliance interpretation, competitive intelligence, or document handling involving sensitive corporate data. In an agentic system, overly broad activation can cause the skill to trigger in situations where narrower, safer, or policy-constrained skills should be used instead, increasing the chance of overreach and unsafe assistance.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The '调用时机' section lists many broad trigger conditions such as writing bids, analyzing tender documents, drafting technical plans, compliance review, and strategy setting, but provides no disambiguation or negative examples. Because this skill operates in a high-stakes business context involving compliance, representations of fact, and competitive strategy, ambiguous routing can lead the system to provide authoritative-seeming guidance outside its safe operational envelope.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The instruction says the agent must keep its document output language in a specific商务/权威风格, and the overall skill content is written as a Chinese bid-writing workflow without offering the user a language or locale choice. This can violate language/locale policy because it imposes a default linguistic mode rather than making it optional or context-dependent.
Content: No source excerpt is available for this finding.