condition-based-waiting — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited condition-based-waiting (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.
A fixed sleep is a guess: too short and it's flaky, too long and it's slow. Wait for the actual condition that tells you the thing is ready.
accepting connections, a line in a log, a file existing, an HTTP 200, a process exiting, a status field flipping.
→ else short wait and retry, up to a sensible deadline. Fail loudly on timeout with a useful message, don't hang forever.
an inotify/watch) over polling.
barrier, a future, a readiness callback). A sleep that "fixes" a flaky test just hides the race.
reader knows what's being awaited and for how long.
Red flag: sleep(5) "to be safe". That's a race waiting to happen — wait on the condition instead.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.