safe-refactoring — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited safe-refactoring (Agent Skill) and scored it 92/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 2 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 2 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Refactoring is improving structure while behaviour stays identical. If behaviour changes, that's a feature/fix — do it separately, with its own test.
add characterization tests that capture current behaviour before you touch it.
of change per step. Don't mix a rename with a logic tweak.
behaviour — revert it and redo it smaller.
one structural improvement you set out to make.
Red flags: tests you had to change to stay green (you altered behaviour); a giant diff touching unrelated code; no tests before you started.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.