Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/run.mjs --sample
Security audit
招投标全案合规审计（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local tender-document checker that reads user-provided JSON and runs disclosed arithmetic and placeholder checks without network use or persistence.
Install this only if you want a local Node-based checker for Chinese bidding-document inputs. It may read sensitive tender content from the input file you provide, so run it only on files you are comfortable processing locally and do not treat its output as a legal or official bid-evaluation decision.
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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- 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
Findings (8)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/run.mjs --sample
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/run.mjs --sample
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 脚本本身不做计算，真正的检查在同目录的 `scripts/engine/tender-compliance-audit.js`（纯 Node 标准库，CommonJS），可以直接引用：
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 脚本本身不做计算，真正的检查在同目录的 `scripts/engine/tender-compliance-audit.js`（纯 Node 标准库，CommonJS），可以直接引用：
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The manifest lists activation phrases such as “投标文件检查”, “标书审查”, and “投标文件审查” without narrowing context or giving exclusion conditions. These are broad descriptions of common work tasks, so they may cause unintended invocation beyond this skill’s specific free-version scope.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
This JSON sample contains bidder names and text entirely in Chinese, including a template phrase in L14, with no indication that the skill is region-specific or that users may choose another language/locale. For a general-purpose sample or skill artifact, this can create an implicit language-policy constraint without user opt-in.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
Rule SQP-3 applies to all file types and covers language or locale policy violations in code and string literals. Using a fixed 'en-US' locale can impose formatting conventions that may conflict with users' expected locale, and the file does not offer configuration or explain why this locale is required.
- Content