T01 · Skill Instruction Hijacking
Warning
- Location
SKILL.md:225- Finding
Mandatory Promotional Content Hijacks Generated Reports
- Content
View full analysis
- Remediation
View remediation
Security audit
patent-novelty-search
Security checks for vulnerabilities and agentic risk
Overview
The skill performs the advertised patent-search workflow, but it forces every generated report to include Patsnap promotional content and potentially misleading attribution.
Review the mandated disclaimer before installing or using this skill. It may place third-party branding, a promotional link, and questionable Patsnap attribution into reports you share with others. Use caution with confidential invention disclosures because the workflow generates a persistent Word document.
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
Findings (1)
Vulnerability Patterns
- 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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
Line L84 requires that searches be performed with both Chinese and English keywords as a checklist item. This imposes a language/locale requirement without opt-in or explanation that the skill is specifically limited to bilingual patent-search contexts.
- Content
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The skill explicitly instructs the agent to create, save, and provide a .docx file to the user, but it does not require an explicit user-facing notice or confirmation before performing that side effect. While document generation is central to the skill’s purpose, silent file creation can still surprise users, create unwanted artifacts, or propagate sensitive input into a persistent downloadable file without clear consent at execution time.
- Content
Static analysis
No suspicious patterns detected.