Security Audit
ntm
github.com/Mrc220/agent_flywheel_clawdbot_skills_and_integrationsTrust Assessment
ntm 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 8 findings: 6 critical, 0 high, 2 medium, and 0 low severity. Key findings include Persistence / self-modification instructions, Arbitrary command execution, Remote code execution: curl/wget pipe to shell.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Static Code Analysis layer scored lowest at 0/100, indicating areas for improvement.
Last analyzed on June 1, 2026 (commit 6a655802). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings8
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Persistence / self-modification instructions Shell RC file modification for persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/ntm/SKILL.md:24 | |
| 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/ntm/SKILL.md:21 | |
| 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/ntm/SKILL.md:534 | |
| 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/ntm/SKILL.md:21 | |
| 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/ntm/SKILL.md:534 | |
| CRITICAL | Skill facilitates disabling critical AI agent safety features The `ntm` skill's configuration examples explicitly show how to launch underlying AI agents (Claude, Codex, Gemini) with flags that bypass their built-in safety mechanisms. Specifically, flags like `--dangerously-skip-permissions`, `--dangerously-bypass-approvals-and-sandbox`, and `--yolo` are documented. While `ntm` acts as an orchestrator, by providing and documenting these options, it enables users to configure agents in a highly insecure manner. An agent running with these disabled safeguards could be susceptible to prompt injection leading to arbitrary command execution, data deletion, or other malicious actions on the host system. This significantly increases the attack surface and potential impact of a successful prompt injection against the orchestrated agents. 1. Strongly advise against using these flags in production or sensitive environments, and provide prominent warnings about their severe security implications. 2. Consider if `ntm` should actively prevent or warn users when these flags are detected in configuration, rather than just documenting them. 3. If possible, `ntm` should integrate with and leverage the agents' safety features rather than providing a direct bypass mechanism. | Static | SKILL.md:252 | |
| MEDIUM | Persistence mechanism: Shell RC file modification Detected Shell RC file modification pattern. Persistence mechanisms allow malware to survive system restarts. Review this persistence pattern. Skills should not modify system startup configuration. | Static | skills/ntm/SKILL.md:24 | |
| MEDIUM | Insecure `curl | bash` installation method The recommended installation method for the `ntm` CLI involves piping the output of `curl` directly to `bash`. This practice is inherently risky as it executes arbitrary code from a remote server (`https://raw.githubusercontent.com/Dicklesworthstone/ntm/main/install.sh`) without prior review, making the installation vulnerable to supply chain attacks if the remote script or the GitHub repository is compromised. While common for CLI tools, it poses a direct execution risk. Recommend users review the installation script before execution. For automated systems or higher security environments, prefer alternative installation methods such as package managers (e.g., Homebrew) or pre-built, signed binaries, which offer better integrity checks and reduce the risk of executing compromised code. | Static | SKILL.md:40 |
Scan History
Embed Code
[](https://skillshield.io/report/b0214503b2c5b80d)
Powered by SkillShield