Trust Assessment
claude-usage 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: 3 critical, 2 high, 0 medium, and 1 low severity. Key findings include Arbitrary command execution, Dangerous call: subprocess.check_output(), Node lockfile missing.
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 Findings6
| 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/lemodigital/claude-usage/scripts/claude-usage.py:155 | |
| CRITICAL | Arbitrary command execution Node.js child_process require 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/lemodigital/claude-usage/bin/claude-usage.js:2 | |
| CRITICAL | Arbitrary command execution Node.js synchronous shell execution 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/lemodigital/claude-usage/bin/claude-usage.js:9 | |
| HIGH | Dangerous call: subprocess.check_output() Call to 'subprocess.check_output()' detected in function 'parse_reset_time'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/lemodigital/claude-usage/scripts/claude-usage.py:155 | |
| HIGH | Arbitrary file read and data exfiltration via --sessions-dir argument The `scripts/claude-usage.py` script accepts a `--sessions-dir` argument which allows a user to specify an arbitrary directory path. The script then attempts to read all files ending with `.jsonl` within this specified directory. If a file's content is not valid JSONL, the script prints the entire malformed line to `sys.stderr` as part of a warning message. This vulnerability allows an attacker to read the content of any file on the system by pointing `--sessions-dir` to a directory containing a symlink to a sensitive file (e.g., `/etc/passwd`, `/home/user/.ssh/id_rsa`) or by creating a file with a `.jsonl` extension containing sensitive data in a controlled directory and then pointing `--sessions-dir` to it. The content of the target file will be exfiltrated line by line through the standard error output. 1. **Restrict `--sessions-dir`:** Limit the `--sessions-dir` argument to paths within the skill's own installation directory or a designated, sandboxed data directory. Disallow absolute paths or paths containing directory traversal sequences (`..`). 2. **Sanitize error output:** When encountering malformed data, do not print the raw content of the problematic line in error messages. Instead, log the file path and a generic error message, or truncate the problematic line to prevent information leakage. 3. **Principle of Least Privilege:** Ensure the skill runs with the minimum necessary file system permissions to prevent unauthorized access to sensitive directories. | LLM | scripts/claude-usage.py:180 | |
| LOW | Node lockfile missing package.json is present but no lockfile was found (package-lock.json, pnpm-lock.yaml, or yarn.lock). Commit a lockfile for deterministic dependency resolution. | Dependencies | skills/lemodigital/claude-usage/package.json |
Scan History
Embed Code
[](https://skillshield.io/report/f0bb778673d13c21)
Powered by SkillShield