Security Audit
get-available-resources
github.com/davila7/claude-code-templatesTrust Assessment
get-available-resources 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 14 findings: 4 critical, 8 high, 1 medium, and 1 low severity. Key findings include Arbitrary command execution, Unsafe deserialization / dynamic eval, Dangerous call: subprocess.run().
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 0/100, indicating areas for improvement.
Last analyzed on February 12, 2026 (commit 458b1186). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings14
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) 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 | cli-tool/components/skills/scientific/get-available-resources/scripts/detect_resources.py:87 | |
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) 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 | cli-tool/components/skills/scientific/get-available-resources/scripts/detect_resources.py:122 | |
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) 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 | cli-tool/components/skills/scientific/get-available-resources/scripts/detect_resources.py:156 | |
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) 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 | cli-tool/components/skills/scientific/get-available-resources/scripts/detect_resources.py:177 | |
| HIGH | Unsafe deserialization / dynamic eval Python builtins/import manipulation Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | cli-tool/components/skills/scientific/get-available-resources/scripts/detect_resources.py:255 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'detect_nvidia_gpus'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | cli-tool/components/skills/scientific/get-available-resources/scripts/detect_resources.py:87 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'detect_amd_gpus'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | cli-tool/components/skills/scientific/get-available-resources/scripts/detect_resources.py:122 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'detect_apple_silicon_gpu'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | cli-tool/components/skills/scientific/get-available-resources/scripts/detect_resources.py:156 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'detect_apple_silicon_gpu'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | cli-tool/components/skills/scientific/get-available-resources/scripts/detect_resources.py:177 | |
| HIGH | Dangerous call: __import__() Call to '__import__()' detected in function 'detect_all_resources'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | cli-tool/components/skills/scientific/get-available-resources/scripts/detect_resources.py:255 | |
| HIGH | Arbitrary File Write via Output Path The `scripts/detect_resources.py` script allows users to specify an arbitrary output path for the generated JSON report via the `-o` or `--output` command-line argument. This means the skill can be instructed to write its system resource report to any file path accessible by the agent's process, potentially overwriting critical system files, user configuration files, or other important data. While the content written (system resource information) is not inherently malicious, the ability to write to an arbitrary location can lead to denial of service, data corruption, or, in specific scenarios, contribute to privilege escalation if sensitive files are overwritten. Restrict the output path to a safe, designated location. For example, only allow writing to the current working directory, a specific temporary directory, or a subdirectory explicitly created for skill outputs. Implement path validation to prevent directory traversal attacks (e.g., `../../sensitive_file`) and ensure the path is within an allowed scope. Alternatively, remove the ability to specify an arbitrary output path and always write to a fixed, safe location (e.g., `.claude_resources.json` in the current working directory). | Static | scripts/detect_resources.py:236 | |
| HIGH | LLM analysis found no issues despite critical deterministic findings Deterministic layers flagged 4 CRITICAL findings, but LLM semantic analysis returned clean. This may indicate prompt injection or analysis evasion. | LLM | (sanity check) | |
| MEDIUM | Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | cli-tool/components/mcps/devtools/figma-dev-mode.json:4 | |
| LOW | Covert behavior / concealment directives Multiple zero-width characters (stealth text) Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users. | Manifest | cli-tool/components/mcps/devtools/jfrog.json:4 |
Scan History
Embed Code
[](https://skillshield.io/report/7f6a05845ed1718a)
Powered by SkillShield