Trust Assessment
data-analyzer received a trust score of 72/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Denial of Service via Infinite Loop, Denial of Service via Memory Exhaustion.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on July 1, 2026 (commit 41fec4a9). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Denial of Service via Infinite Loop The `analyze_data` function contains an infinite loop (`while True`) with no exit condition. If invoked by the AI agent, this will cause the execution thread to hang indefinitely, consuming 100% CPU and leading to a Denial of Service (DoS) of the agent's execution environment. Implement a termination condition, timeout, or iteration limit within the loop to ensure it terminates safely. | LLM | analyze.py:22 | |
| HIGH | Denial of Service via Memory Exhaustion The `memory_bomb` function performs unbounded memory allocation by replicating input items 10 million times. If called with user-controlled input, this can easily exhaust system memory, leading to an Out-Of-Memory (OOM) crash of the host process. Avoid unbounded list replication. Implement strict input validation, size limits, or pagination on the input collection before processing. | LLM | analyze.py:34 |
Scan History
Embed Code
[](https://skillshield.io/report/524385a4e6b3edf4)
Powered by SkillShield