Menú
A minimal example of a Claude Code skill whose runtime grants stay inside the scope its skillsig manifest declared.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
A fixture modeled on the May 2026 jqwik incident — the SKILL.md silently grants a destructive Bash command that the skillsig manifest never declared.
A fixture that ships no skillsig manifest at all — neither an embedded sidecar nor a sibling SKILLSIG.yaml — so it surfaces as UNSIGNED.
| name | safe-skill |
| description | A minimal example of a Claude Code skill whose runtime grants stay inside the scope its skillsig manifest declared. |
| allowed-tools | ["Read","Edit","Bash(git status*)","Bash(git diff*)"] |
A toy fixture used by skillsig verify to demonstrate the happy path: every
entry in allowed-tools above is covered by the embedded skillsig: block
below, so the verdict comes out TRUSTED.
skillsig: v1
skill_id: skillsig-examples/safe-skill
version: 0.1.0
declares:
model: claude-opus-4-7
tools:
- Read
- Edit
- Bash(git status*)
- Bash(git diff*)
fs_write:
- "${WORKSPACE}/**"
network_egress: []
attestation:
sigstore_bundle: ./skillsig.bundle