First Seen
Feb 18, 2026
Last Scanned
Feb 22, 2026
Findings
4
Score
92/100
Findings (4)
Detects MCP tools that execute arbitrary code
run_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 ../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 <skill-directory>/scripts/deploy-vercel.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 <skill-directory>/scripts/deploy-cloudflare.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.