zulipchat-notifyme-0304b9 — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited zulipchat-notifyme-0304b9 (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
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.
Use this skill when you explicitly want to post to the bound Zulip topic outside the default lifecycle hooks.
ZULIPCHAT_SESSION_ID from the shell.session.
Interpret $ARGUMENTS as either:
<category> :: <message><message> for a plain message categorySupported categories:
messagestartedblockedwaitingcompletedfailedagent_message(session_id=..., category=..., content=...).request_user_input(...) instead.
Questions use /reply REQUEST_ID YOUR ANSWER; approvals use /approve REQUEST_ID or /deny REQUEST_ID. Call wait_for_response(request_id=..., timeout_seconds=30) and retain the same request ID after a timeout. Do not post duplicate prompts.
Poll steering with auto_ack=False in the bound session. Handle each event, then acknowledge its ID with ack_event_ids in the same session scope. Replayed events must not repeat completed external actions. A delivered partial result includes its message ID and retry_safe=False; inspect that result before retrying.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.