T03 · Remote Payload Retrieval and Execution
Warning
- Location
SKILL.md:39- Finding
Unpinned Remote Repository Retrieval and Execution
- Content
View full analysis
- Remediation
View remediation
Security audit
Ai Intelligent Backup Automation
Security checks for vulnerabilities and agentic risk
Overview
This backup skill is review-worthy because it asks users to run unreviewed remote code for high-impact backup and restore operations without clear safeguards.
Install only if you are comfortable reviewing the cloned repository and dependencies yourself first. Run it in an isolated, non-privileged environment, avoid production restore tests unless explicitly configured and backed up, and require clear confirmation before any restore or overwrite action.
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
- 92% confidence
- Finding
The skill advertises automated backup and restore testing, which are operations that can modify, overwrite, delete, or stress real data and systems, yet it provides no user-facing warnings, safeguards, or scope limitations. In this context, the omission can mislead users into running destructive operations without understanding risks to data integrity, retention, or production availability.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill description is overly vague and does not clearly define what the backup automation skill will do, when it should activate, or what systems and data it is allowed to access. For a skill involving backup and restore operations, unclear scope increases the risk of unintended invocation, excessive permissions, or unsafe handling of sensitive data during automation.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The description and headings are entirely in Chinese, which imposes a language choice on users without any opt-in or explanation that the skill is intended only for a Chinese-speaking or region-specific audience. This can violate language/locale policy when no user choice or documented constraint is provided.
- Content