Trust Assessment
base received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 6 findings: 5 critical, 0 high, 1 medium, and 0 low severity. Key findings include Arbitrary command execution, Remote code execution: curl/wget pipe to shell, Resource Exhaustion via Malicious External API Responses.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Static Code Analysis layer scored lowest at 10/100, indicating areas for improvement.
Last analyzed on February 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings6
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Remote code download piped to interpreter Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/spirosrap/base/scripts/base.sh:151 | |
| CRITICAL | Arbitrary command execution Remote code download piped to interpreter Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/spirosrap/base/scripts/base.sh:163 | |
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Static | skills/spirosrap/base/scripts/base.sh:14 | |
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Static | skills/spirosrap/base/scripts/base.sh:151 | |
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Static | skills/spirosrap/base/scripts/base.sh:163 | |
| MEDIUM | Resource Exhaustion via Malicious External API Responses The skill makes calls to external RPC (`https://1rpc.io/base`) and price APIs (`https://api.coingecko.com`). The responses from these APIs are processed by `python3 -c` commands (e.g., `json.load`, `int("$wei", 16)`). If a malicious or compromised external API returns an extremely large or malformed response (e.g., a multi-gigabyte JSON string or a very long hexadecimal number), the `python3` interpreter could attempt to load it entirely into memory, leading to excessive memory consumption and a denial-of-service (DoS) for the skill's execution environment. The `curl` commands do not implement size limits, making this a credible supply chain risk. Implement size limits for `curl` responses (e.g., `--max-filesize`). For Python processing, consider using libraries that handle large data streams more efficiently or implement explicit size checks before parsing. Alternatively, use `jq` with resource limits if available, as it is listed as a required binary in the manifest. | LLM | scripts/base.sh:26 |
Scan History
Embed Code
[](https://skillshield.io/report/d9a8098cc341637a)
Powered by SkillShield