Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - `SKILL.md`：本文件，主指令。
Security audit
gov-procurement-doc-assistant
Security checks for vulnerabilities and agentic risk
Overview
This is a disclosed tender-document analysis skill with no hidden install or persistence behavior, though users should treat uploaded bid materials as sensitive.
Install this only for Chinese government procurement or tender-document analysis. Avoid uploading confidential bid materials unless the assistant, OCR, and configured knowledge-base workflow are approved for that data, and treat legal and pricing outputs as review aids rather than final legal, commercial, or bidding decisions.
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
- 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 (8)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 87% confidence
- Finding
The display name, description, examples, and operating instructions are entirely written in Chinese and present trigger phrases only in Chinese, which implies a fixed language/locale behavior. The file does not state that the skill is China-specific as a documented language constraint, nor does it offer users a language-choice or opt-in mechanism.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The trigger phrase set includes broad natural-language patterns such as “标书解读 / 分析这份标书,” which can match common user requests beyond a narrowly scoped procurement-analysis workflow. This can cause unintended invocation on unrelated or only partially related documents, increasing the chance of unnecessary document ingestion, accidental exposure of sensitive tender materials, or incorrect tool selection.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The coze trigger list contains short, generic commands like “投标建议” and “出风险清单,” which overlap with many ordinary business-analysis requests and can cause the skill to activate outside its intended boundaries. In this skill’s context, unintended activation is more concerning because uploaded bid documents may contain commercially sensitive information and the skill performs specialized compliance interpretation that may supersede more appropriate tools.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 84% confidence
- Finding
The entire skill reference is written only in Chinese and provides user-facing prompt templates exclusively in Chinese, with no indication that the user can choose another language or locale. This can violate a language/locale policy when the skill is used in multilingual environments without explicit opt-in or justification.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
This markdown file contains user-facing operational guidance only in Chinese and does not indicate that the user can choose another language. Under the policy rule for language or locale constraints, forcing a specific language without user opt-in is a natural-language policy violation.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
The document title and all operational test descriptions are written exclusively in Chinese, with no indication that users may choose another language or locale. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy concern.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The natural-language content of the skill is fully presented in Chinese, and the README does not mention any option for users to receive instructions or outputs in another language. Under the policy, a skill that effectively forces a specific language without user opt-in can be considered a locale/language policy issue.
- Content
Static analysis
No suspicious patterns detected.