card-tones — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited card-tones (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 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.
Run .skills/card-tones/scripts/preview_card_tones.sh from the project root. It renders the share card in both tones so a renderer change can be eyeballed in one pass. Design proof only — neither card is a publishable result.
.skills/card-tones/scripts/preview_card_tones.sh <neg-run-dir> <out-dir>
# e.g.
.skills/card-tones/scripts/preview_card_tones.sh runs/L0-headline-haiku /tmp/cardcheckWrites share_card.neg.{png,svg} and share_card.pos.{png,svg} under <out-dir>.
corona tone-gated OFF.
posbranch (purple core plus the faint cyan corona). It borrows the neg run's bare chart and carries a fabricated positive-token summary purely so the graph and lens-flare compose — the number is a render fixture, never a published metric. Staged in a temp dir and removed on exit.
The shared .skills/scripts/preview_card.sh (walks Chrome → sips → SVG-only), which is the single card renderer the preview_card and finish skills also use.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.