Incomplete referenced artifact analysis
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - 公开采访/最近言论/万达恒大/人民币观点/中美关系 → `references/dimensions/public-statements.md`
Security audit
shanweijian-investing
Security checks for vulnerabilities and agentic risk
Overview
ClawScan rates this investing-focused skill benign because the scanners found no clear harmful behavior, though one referenced document was only partly analyzed and a broad question-routing rule was flagged.
The verdict is benign with medium confidence, but the scan is incomplete: 29 of 30 components were fully inspected, and one reference was only partly inspected. Consider whether the broad “why” routing fits your use, and keep in mind that a benign verdict does not mean risk-free.
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
- 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 (3)
Incomplete referenced artifact analysis
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - `references/dimensions/public-statements.md` — 公开采访与文章观点库（2023-2026）：万达收购案、恒大、人民币升值建议、中美关系、HBR访谈
L009 routes any user question containing “为什么” (“why”) to this reference without explicitly limiting the subject.
Low
- Category
- Trigger Abuse
- Confidence
- 93% confidence
- Finding
“Why” is a common everyday question rather than a domain-specific trigger. Although the document concerns Shan Weijian’s books and investment thinking, this routing instruction does not require that context, so it could lead to irrelevant reference lookups.
- Content