First Seen
Feb 18, 2026
Last Scanned
Feb 22, 2026
Findings
6
Score
84/100
Findings (6)
Detects shell metacharacters (pipes, backticks, subshells) in MCP server command arguments
"Command":"Get-Process | Sort-Object CPU -Descending |Remove credentials (API keys, tokens, passwords) from MCP server configuration. Use environment variable references (e.g., ${API_KEY}) or a secrets manager instead of inline values.
Likely FP if the credential value is a placeholder (e.g., your-api-key-here, sk_test_xxx) in example configuration.
Detects MCP tools that execute arbitrary code
execute_commandRestrict code execution tools to specific languages and sandbox the runtime environment. Use a container or VM-based sandbox instead of running code directly on the host.
Likely FP if the MCP tool is a dedicated code runner (e.g., Jupyter kernel) with documented sandboxing and no network access.
Detects execution of shell script files via bash/sh command or direct invocation
bash
{baseDir}/scripts/setup.shReplace direct shell script execution with a language-native implementation or a sandboxed executor. If shell scripts must run, restrict them to a vetted allowlist with integrity checks.
Likely FP if the match references running a script that is part of the skill's own repository (e.g., ./setup.sh) with clear, auditable contents.
Detects execution of shell script files via bash/sh command or direct invocation
bash
{baseDir}/scripts/setup.shReplace direct shell script execution with a language-native implementation or a sandboxed executor. If shell scripts must run, restrict them to a vetted allowlist with integrity checks.
Likely FP if the match references running a script that is part of the skill's own repository (e.g., ./setup.sh) with clear, auditable contents.
Detects MCP tools that execute arbitrary code
execute_commandRestrict code execution tools to specific languages and sandbox the runtime environment. Use a container or VM-based sandbox instead of running code directly on the host.
Likely FP if the MCP tool is a dedicated code runner (e.g., Jupyter kernel) with documented sandboxing and no network access.
Detects MCP tools that execute arbitrary code
execute_commandRestrict code execution tools to specific languages and sandbox the runtime environment. Use a container or VM-based sandbox instead of running code directly on the host.
Likely FP if the MCP tool is a dedicated code runner (e.g., Jupyter kernel) with documented sandboxing and no network access.