Security audit

招投标助手（Bid Assistant）

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language bid-assistance skill that handles tender documents and business materials in a disclosed, purpose-aligned way, with human confirmation required for high-impact decisions.

Before installing, confirm that only authorized users can submit tender files, company qualifications, historical bids, pricing material, and customer information. Configure retention, audit logs, masking, and Feishu permissions clearly, and keep final bid/no-bid decisions, pricing, commitments, seals, and submission under human approval as the skill already requires.

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
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (18)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The README explicitly describes users uploading tender notices and tender documents, which commonly contain sensitive commercial, personal, and confidential procurement data, but it does not provide a clear warning about data classification, retention, access control, or approved handling channels. In a bid-assistance workflow, this omission can lead users to submit regulated or confidential documents into the system without understanding privacy, secrecy, or compliance constraints, increasing the risk of unauthorized disclosure or improper processing.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The manifest defines the mission and scenarios but does not specify clear activation boundaries, triggers, or gating conditions for when the skill should engage. In a high-stakes bidding workflow that handles sensitive documents and can generate compliance-relevant outputs, ambiguous invocation scope increases the risk of accidental activation on unrelated messages, over-collection of files, or premature processing of confidential tender materials.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The file’s natural-language instructions are fully Chinese from the title through all operational steps, and there is no indication that users may choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This manifest presents all user-facing skill names and purpose descriptions in Chinese, which effectively forces a specific language for understanding and invocation context. There is no indication that the skill is region-specific or that users may opt into another language, so this appears to violate the language/locale policy for natural-language content.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The prompt is written entirely in Chinese and defines the assistant role in Chinese without indicating that users may choose another language. This creates a natural-language locale policy issue because the skill appears to require a specific language by default rather than offering a language preference or opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: This markdown template hard-codes all user-facing headings and labels in Chinese, which can violate language/locale policy when no user opt-in or documented regional justification is provided. Because the file contains only Chinese UI text and no indication of optional localization, it appears to force a specific language.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: This markdown template uses Chinese headings throughout and does not indicate that the language is optional, user-selected, or required for a region-specific workflow. 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

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: This markdown template is entirely written in Chinese and provides no indication that language selection is optional or constrained to a China-specific workflow. That can violate a language/locale policy when a skill implicitly forces one language for all users without opt-in.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The invocation example is broad enough that ordinary user language could trigger the skill without clear gating, such as requiring explicit intent, approved context, or attachment presence. In a bid-assistant workflow, accidental activation could cause unintended processing of sensitive tender documents or produce procurement guidance when the user did not mean to invoke the full workflow.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The follow-up phrase '根据刚才的招标文件，帮我拆投标任务' relies on conversational context and lacks strong activation boundaries, which can let the skill trigger on routine follow-up language. This is risky because context carryover may cause the agent to act on stale, unrelated, or incorrectly scoped tender materials and generate operational tasking without deliberate user confirmation.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The review request is broadly phrased and could match common proofreading or QA language without clearly limiting what artifact should be reviewed or when the skill should activate. In this skill's context, that can expose sensitive bid drafts to unintended analysis and may produce compliance or deviation judgments on the wrong document scope.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The entire skill workflow is written as a Chinese-only operating specification, with no indication that users may choose another language or locale. Under the policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale restriction is explicitly documented and justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: This markdown file presents the skill demo script and user-facing invocation entirely in Chinese, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the policy rule for language or locale constraints, forcing a single language without opt-in can be 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: 79% confidence
Finding: The skill metadata and user-facing naming are entirely in Chinese, with no indication that users may choose another language or that the skill is intentionally restricted to a Chinese-language environment. This can be a natural-language policy issue when a skill effectively imposes a locale without explicit opt-in or documented regional justification in the file.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The README content is entirely in Chinese and does not mention that the skill is intended only for Chinese-speaking users or offer any language/locale option. Per the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is explicitly documented and justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This markdown template is entirely written in Chinese, including the document title and all section headers, which implies the skill output is fixed to a specific language. The policy requires flagging language or locale constraints when they are imposed without an explicit user choice or documented justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: This markdown template is entirely Chinese-language content and does not indicate that users may select another language or that the template is intended only for a Chinese-language workflow. Under the policy, forcing a specific language without user opt-in can be 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: 93% confidence
Finding: The entire report template uses Chinese section headings and provides no indication that language is selectable or that the skill is intentionally limited to Chinese-speaking users. This can violate a language/locale policy when a skill forces a specific language without user opt-in or documented regional justification.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.