Trust Assessment
radio-copilot 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 21 findings: 8 critical, 12 high, 1 medium, and 0 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 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings21
| 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/davestarling/satellite-copilot/scripts/orchestrator.py:68 | |
| 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/davestarling/satellite-copilot/scripts/orchestrator.py:72 | |
| 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/davestarling/satellite-copilot/scripts/radio_scheduler.py:62 | |
| 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/davestarling/satellite-copilot/scripts/radio_scheduler.py:80 | |
| 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/davestarling/satellite-copilot/scripts/radio_scheduler.py:94 | |
| 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/davestarling/satellite-copilot/scripts/radio_scheduler.py:178 | |
| 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/davestarling/satellite-copilot/scripts/radio_scheduler.py:170 | |
| CRITICAL | Local Command Injection via subprocess.run(shell=True) The `radio_scheduler.py` script executes a user-defined command from `config.json` (`cap.get("command")`) using `subprocess.run` with `shell=True`. This allows an attacker to inject arbitrary shell commands into the `command` field of the `capture` configuration in `config.json`, leading to arbitrary code execution on the host machine where the skill is running. This is a severe local command injection vulnerability. Avoid `shell=True` when executing user-controlled commands. Instead, pass the command and its arguments as a list to `subprocess.run` (e.g., `subprocess.run(["/bin/sh", "-c", cmd_string])` if shell features are truly needed, but then `cmd_string` must be carefully sanitized, or better, `shlex.split(cmd_string)` if the command is a simple string that can be split into arguments). The safest approach is to define a fixed set of commands and parameters, and validate user input against these. | LLM | scripts/radio_scheduler.py:160 | |
| 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/davestarling/satellite-copilot/scripts/radio_scheduler.py:170 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'send_whatsapp'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/davestarling/satellite-copilot/scripts/orchestrator.py:68 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'run'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/davestarling/satellite-copilot/scripts/orchestrator.py:72 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'run_pass_predictor'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/davestarling/satellite-copilot/scripts/radio_scheduler.py:80 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'send_notify'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/davestarling/satellite-copilot/scripts/radio_scheduler.py:94 | |
| HIGH | Dangerous call: subprocess.check_output() Call to 'subprocess.check_output()' detected in function 'run_pass_predictor'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/davestarling/satellite-copilot/scripts/radio_scheduler.py:62 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'main'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/davestarling/satellite-copilot/scripts/radio_scheduler.py:178 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.clawdbot/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/davestarling/satellite-copilot/SKILL.md:11 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.clawdbot/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/davestarling/satellite-copilot/SKILL.md:12 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.clawdbot/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/davestarling/satellite-copilot/SKILL.md:13 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.clawdbot/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/davestarling/satellite-copilot/SKILL.md:25 | |
| HIGH | Remote Command Injection via SSH remoteCommand The `ssh` function in `orchestrator.py` executes a `remote_cmd` string, which is sourced directly from the `config.json` file (e.g., `sat_cfg.get("capture", {}).get("remoteCommand")`). While the local `subprocess.run` uses a list of arguments, the `remote_cmd` itself is executed by the remote shell. A malicious entry in `config.json` for `remoteCommand` could lead to arbitrary command execution on the remote host. The `remote_cmd` should be carefully sanitized or, preferably, the remote execution should be limited to a predefined set of safe commands or a dedicated API. If arbitrary commands are truly needed, the user must be explicitly warned about the security implications of configuring this field. For example, pass arguments to a known remote script instead of executing an arbitrary string. | LLM | scripts/orchestrator.py:70 | |
| MEDIUM | Unpinned Node.js Dependencies The `pass_predictor.mjs` script imports `node-fetch` and `satellite.js` without specifying exact versions (e.g., in a `package.json` with pinned versions). This can lead to non-deterministic builds and potential security vulnerabilities if a new version of these libraries introduces breaking changes or security flaws. Create a `package.json` file in the skill's root directory (or `scripts` directory) and add `node-fetch` and `satellite.js` as dependencies with pinned versions (e.g., `^3.0.0` or `~3.0.0` for minor/patch updates, or exact versions for maximum stability). Use `npm install` or `yarn install` to generate a lock file. | LLM | scripts/pass_predictor.mjs:10 |
Scan History
Embed Code
[](https://skillshield.io/report/bf2c193f51765ad0)
Powered by SkillShield