Back to skill

Security audit

gov-procurement-advisor

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Chinese government-procurement document review skill with no executable code, hidden persistence, or unrelated data access.

Install only if you need Chinese government-procurement document review. Verify important legal conclusions against current official sources or a qualified professional, especially for engineering projects that may overlap with bidding-law rules.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The display name, description, role, and operating instructions are all written exclusively in Chinese and direct the assistant to respond in that language/style. This is a natural-language locale constraint, and the file does not offer any user opt-in or alternative language choice, nor does it explicitly justify the restriction as a required region-specific language policy.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill says out-of-scope legal regimes must be refused, yet another section instructs the agent to process those same matters. Such internal policy conflict is dangerous because the model may follow the more specific later instruction and silently bypass safety boundaries, producing unauthorized or unreliable legal analysis.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill metadata and boundary section state it is only applicable to the 《政府采购法》 regime, but later instructions say engineering projects should also trigger retrieval and conflict analysis under the 《招标投标法》 regime. This creates contradictory scope handling that can cause the agent to provide advice outside its declared competence, increasing the chance of incorrect legal guidance and unsafe user reliance.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The manifest presents the skill name and full description only in Chinese, with no indication that users can choose another language or that the skill is restricted to Chinese-speaking users. This can violate language/locale policy expectations when a skill is exposed in broader environments without explicit opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The README is entirely written as a Chinese-only skill persona and workflow description, with no indication that users may choose another language or locale. Under the policy rule for natural-language constraints, this reads as a default language restriction rather than an opt-in or clearly justified locale-specific language choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.