SkillMD Review · sourcesage-cli
our safety review · skill by Sunwood-ai-labs
Commands are read-only documentation generation using uv run on a local tool; no secrets, network calls, or destructive operations.
reviewed 2026-08-22
What the verdicts mean
No risky instructions — documentation or standard, read-only development-tool usage.
Legitimate purpose with real capabilities (runs scripts, calls services, or handles credentials). Read the skill before installing.
Risky patterns beyond the skill's job — elevated privileges, config changes, or bypassed confirmations. Review carefully.
Instructions a safe skill should never contain — injection, exfiltration, or destructive commands. Don't install unless you've verified the source.
Could not be confidently assessed — treat as unreviewed and inspect the SKILL.md yourself.