delegating-to-subagents — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited delegating-to-subagents (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.
When a task has independent parts, delegate them to subagents (the Agent tool) instead of doing everything in one context. Each gets an isolated context window, so you stay focused on coordination.
files/subsystems/bugs) and can run without each other's intermediate state. If they share tightly-coupled state, do it inline instead.
context it needs (don't assume it sees this conversation), constraints ("don't touch X"), and what to return. Narrow scope = reliable result.
on another's output.
result yourself — subagents can make systematic mistakes. Then run the suite.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.