T03 · Remote Payload Retrieval and Execution
Error
- Location
SKILL.md:39- Finding
Unpinned Remote Payload Retrieval and Execution
- Content
View full analysis
- Remediation
View remediation
Security audit
Ai Intelligent Ad Optimization
Security checks for vulnerabilities and agentic risk
Overview
This advertising optimization skill has a plausible purpose, but it asks users to run unreviewed remote code and describes budget-affecting automation without clear controls.
Review this carefully before installing. Do not run the documented git clone, pip install, or python app.py steps in an environment with credentials, ad-platform access, or sensitive files unless the remote repository and dependencies are independently reviewed, pinned, and isolated. Treat any live ad optimization as requiring explicit human approval, spend limits, monitoring, and rollback planning.
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 (4)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The skill describes live ad optimization capabilities including intelligent bidding, budget allocation, and ROI analysis, but provides no warning that using it may directly affect spend, delivery, or campaign performance. In an advertising context, missing disclosure about budget-affecting automation can lead users to enable or rely on the skill without understanding financial and operational consequences.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The description promises automatic ad optimization, A/B testing, and ROI analysis without clarifying boundaries, approval requirements, or when actions should be taken. In an agent setting, overly broad invocation language can cause the skill to be applied in unintended contexts or encourage autonomous optimization actions that change campaigns without explicit user confirmation.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The skill metadata and documentation are entirely in Chinese, with no indication that language selection is optional or that the skill is intended only for a Chinese-speaking or China-specific context. This can violate language/locale policy when a skill implicitly forces a specific language without user opt-in or documented justification.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 80% confidence
- Finding
The skill name metadata and description are presented in Chinese, and the tags include 'chinese', but there is no indication that language choice is optional or that the skill is region-specific. This may violate language/locale policy expectations if the skill assumes a fixed language without user consent.
- Content
Static analysis
No suspicious patterns detected.