Trust Assessment
ops-dashboard 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 7 findings: 3 critical, 3 high, 1 medium, and 0 low severity. Key findings include Arbitrary command execution, Dangerous call: subprocess.run(), Skill can access and report metadata on arbitrary filesystem paths.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest 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 Findings7
| 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 | skills/crimsondevil333333/ops-dashboard/scripts/ops_dashboard.py:32 | |
| 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 | skills/crimsondevil333333/ops-dashboard/scripts/ops_dashboard.py:45 | |
| 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 | skills/crimsondevil333333/ops-dashboard/tests/test_ops_dashboard.py:11 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'get_git_status'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/crimsondevil333333/ops-dashboard/scripts/ops_dashboard.py:32 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'get_recent_commits'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/crimsondevil333333/ops-dashboard/scripts/ops_dashboard.py:45 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'run_cli'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/crimsondevil333333/ops-dashboard/tests/test_ops_dashboard.py:11 | |
| MEDIUM | Skill can access and report metadata on arbitrary filesystem paths The `ops-dashboard` skill, particularly functions like `get_disk_usage` and `get_top_directories`, accepts a user-controlled `--workspace` argument. This argument, after `expanduser().resolve()`, can point to any directory on the filesystem. The skill then proceeds to gather and report metadata such as total/used/free disk space, and the names and sizes of top-level directories within the specified workspace. While it does not read file *contents*, this capability allows for broad filesystem reconnaissance, potentially revealing sensitive system structure, resource usage, and the presence/size of critical directories (e.g., `/etc`, `/var`, `/root`, `/usr`). This constitutes an excessive permission scope for a skill that might be invoked by an LLM with user-provided input, leading to information disclosure. Implement strict path validation or sandboxing for the `--workspace` argument to restrict it to a predefined, safe directory (e.g., the skill's own directory or a temporary, isolated workspace). Alternatively, if broad filesystem access is intended, ensure the LLM orchestration layer explicitly understands and controls the `workspace` argument to prevent malicious or accidental exposure of sensitive system information. | LLM | scripts/ops_dashboard.py:79 |
Scan History
Embed Code
[](https://skillshield.io/report/d34c2d3b40c90721)
Powered by SkillShield