T03 · Remote Payload Retrieval and Execution
Error
- Location
SKILL.md:36- Finding
Unpinned Remote Code and Dependency Retrieval Followed by Local Execution
- Content
View full analysis
- Remediation
View remediation
Security audit
Ai Intelligent Audit System
Security checks for vulnerabilities and agentic risk
Overview
The skill describes a legitimate audit tool, but its install steps execute unpinned remote code that is not included in the reviewed package.
Review the referenced GitHub repository and dependencies before installing, pin to a trusted commit or release, and run it only in an isolated environment without unnecessary secrets or sensitive audit records. Treat generated audit material as confidential unless the publisher documents storage, logging, retention, and access controls.
Vulnerability Patterns
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- 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
- 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
- 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)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The skill explicitly targets internal audit, financial audit, compliance audit, and IT audit use cases, which commonly involve highly sensitive corporate, financial, operational, and potentially personal data. The description provides installation and usage context but omits any warning about sensitive data handling, retention, access control, or safe input practices, which can lead users to expose confidential audit material without appropriate safeguards.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 87% confidence
- Finding
The manifest description and the entire markdown content are written in Chinese, which effectively imposes a language constraint on users. There is no indication that the skill supports multiple languages, offers user choice, or is intentionally limited to a Chinese-language audience for a documented regional reason.
- Content
Vague Triggers
Low
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The description "AI intelligent ai-intelligent-audit-system" is too generic to communicate what the skill does, when it should be invoked, or what boundaries apply. For an internal audit and compliance skill, vague scope increases the risk of overbroad activation, misuse in sensitive workflows, and weak operator understanding of data handling expectations.
- Content
Static analysis
No suspicious patterns detected.