customer-status — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited customer-status (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 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.
Principle: "Narrow scope, high impact." One synthesised view across all accounts, so you can spot what needs attention without channel-hopping.
Produces a dashboard-style overview of active customer accounts and internal projects for the manager's team.
If any MCP connector is unavailable, follow the connector unavailability protocol in references/operating-principles.md.
Read from manager-context/:
sources.md: customer/project channels, account mappingsmanager-profile.md: team members and their account assignmentsteam/: individual team member profiles and project assignmentsIf no manager-context exists:
⚠️ No manager context found. Run /setup first so I know which accounts and channels to monitor.
I can still search broadly, but results will be less targeted.From manager-context, get the list of active accounts/projects and their:
If filtering by account or team member, narrow the scope.
For each active account, gather:
Slack (last 7 days):
Gmail (last 14 days):
Notion:
Google Drive:
For each account, determine a health signal based on evidence:
Important: These are signals, not diagnoses. Always show the evidence that led to the assessment.
Read references/output-template.md for the full output template structure.
Spawn a sub-agent to review the customer status overview with fresh eyes. The reviewer should:
Incorporate the reviewer's feedback before presenting the final overview.
Here's your customer status overview. Want me to:
- Dig deeper into any specific account?
- Prep for a conversation with [team member] about [account]?
- Check email threads for a specific customer?Read references/operating-principles.md for shared operating principles (data scope, DM flagging, signals vs diagnoses, connector unavailability).
Additional notes specific to this skill:
(from DM).~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.