example-skill — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited example-skill (Agent Skill) and scored it 87/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 3 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 3 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.
This skill demonstrates the canonical structure for a compliant Agent Skill.
When analyzed by agent-scaffolders, this fixture MUST:
This skill uses Progressive Disclosure. Load only what you need:
./acceptance-criteria.md./analysis-notes.mdIdentify what the user needs:
analyze-plugin against this fixture and confirm expected scoresPresent the relevant output based on the user's goal. Always confirm the acceptance criteria in ./acceptance-criteria.md are satisfied before marking complete.
| Principle | Implementation |
|---|---|
| Progressive Disclosure | Deep content in references/, lean SKILL.md |
| Acceptance Criteria Gate | Explicit checklist in ./acceptance-criteria.md |
| Structured Output | Table-formatted step summary |
| Trigger Vocabulary | Rich description with multiple phrasing variants |
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.