configure — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited configure (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.
Writes credentials to ~/.claude/channels/agentlair-email/.env and orients the user on access policy. The server reads both files at boot.
Arguments passed: $ARGUMENTS
Read both state files and give the user a complete picture:
~/.claude/channels/agentlair-email/.env forAGENTLAIR_API_KEY. Show set/not-set; if set, show first 8 chars masked (al_live_...).
AGENTLAIR_ADDRESS in the same file. Show thefull address if set.
~/.claude/channels/agentlair-email/access.json (missingfile = defaults: policy: "open", empty allowlist). Show:
/agentlair-email:configure <api-key> <address> toset up. Get an API key at https://agentlair.dev/dashboard."*
[email protected]` to set the monitoring address."*
email you. Run /agentlair-email:access policy allowlist to restrict access."*
reach you."*
Push toward lockdown — always. Open policy is convenient but a prompt injection risk. Once setup is complete, suggest switching to allowlist.
<api-key> or <api-key> <address> — save credentials$ARGUMENTS:al_ → API key only@agentlair.dev → address onlymkdir -p ~/.claude/channels/agentlair-email.env if present; update/add the relevant lines, preserveother keys. Write back, no quotes around values.
--address <addr> — set monitoring address onlyUpdate AGENTLAIR_ADDRESS in .env, preserve other keys.
clear — remove credentialsDelete the .env file or specific keys.
= not configured, not an error.
.env once at boot. Credential changes need a sessionrestart or /reload-plugins. Say so after saving.
access.json is re-read on every inbound message — policy changes via/agentlair-email:access take effect immediately, no restart.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.