Trust Assessment
codex-account-switcher 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 13 findings: 6 critical, 6 high, 0 medium, and 1 low severity. Key findings include Unsafe environment variable passthrough, Arbitrary command execution, Credential harvesting.
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 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings13
| 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/odrobnik/codex-account-switcher/codex-accounts.py:394 | |
| 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/odrobnik/codex-account-switcher/codex-accounts.py:403 | |
| 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/odrobnik/codex-account-switcher/codex-accounts.py:458 | |
| 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/odrobnik/codex-account-switcher/codex-accounts.py:461 | |
| 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/odrobnik/codex-account-switcher/codex-accounts.py:567 | |
| CRITICAL | Credential harvesting Bulk environment variable dump Skills should only access environment variables they explicitly need. Bulk environment dumps (os.environ.copy, JSON.stringify(process.env)) are almost always malicious. Remove access to Keychain, GPG keys, and credential stores. | Manifest | skills/odrobnik/codex-account-switcher/codex-accounts.py:400 | |
| HIGH | Unsafe environment variable passthrough Bulk environment variable harvesting Minimize environment variable exposure. Only pass required, non-sensitive variables to MCP servers. Use dedicated secret management instead of environment passthrough. | Manifest | skills/odrobnik/codex-account-switcher/codex-accounts.py:400 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'do_browser_login'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/odrobnik/codex-account-switcher/codex-accounts.py:394 | |
| HIGH | Dangerous call: subprocess.Popen() Call to 'subprocess.Popen()' detected in function 'do_browser_login'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/odrobnik/codex-account-switcher/codex-accounts.py:403 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'do_device_login'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/odrobnik/codex-account-switcher/codex-accounts.py:458 | |
| HIGH | Dangerous call: subprocess.Popen() Call to 'subprocess.Popen()' detected in function 'do_device_login'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/odrobnik/codex-account-switcher/codex-accounts.py:461 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function '_get_quota_for_account'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/odrobnik/codex-account-switcher/codex-accounts.py:567 | |
| LOW | Skill manages sensitive authentication tokens The skill's manifest explicitly states its core functionality involves reading and writing sensitive authentication tokens to `~/.codex/auth.json` and `~/.codex/accounts/*.json`. The `codex-accounts.py` script, specifically the `get_account_info` function, implements this by loading JSON data from these paths and extracting `id_token` and other sensitive information. While this is the intended and necessary functionality for an account switcher, it signifies that the skill has direct access to and manages highly sensitive user credentials. Any compromise of the skill's execution environment or an undiscovered vulnerability within the skill could lead to the exposure or misuse of these tokens. Ensure the skill's execution environment is secure and isolated. Implement robust access controls for the `~/.codex` directory. Regularly audit the skill's code for any unintended data exfiltration or insecure handling of these sensitive tokens. Users should be fully aware of the high-privilege nature of this skill and the sensitive data it manages. | LLM | codex-accounts.py:50 |
Scan History
Embed Code
[](https://skillshield.io/report/448f7134ee5f5ecd)
Powered by SkillShield