email-triage
Scan and process unread emails. Scores by priority (VIP, urgency, deadlines), classifies, saves relevant emails as vault notes, and generates a triage report. Triggers: EN: "check my email", "what's in my inbox", "process emails", "email triage", "anything urgent in email?", "save important emails". IT: "controlla le email", "cosa c'è nella mia inbox", "triage email", "processa le email", "email urgenti". FR: "vérifier mes emails", "trier mes emails". ES: "revisar mi correo", "triaje de emails". DE: "E-Mails prüfen", "Posteingang sichten". PT: "verificar meus emails", "triagem de emails".
68
82%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Yes—outsider-authored email bodies/subjects from external senders are read at runtime via `gws gmail users messages get` / `gws ... threads get` / `hey-thread` / `gmail_read_message` / `gmail_read_thread`, then synthesized into the agent’s LLM context for prioritization, classification, and note generation.
- Repository
- gnekt/My-Brain-Is-Full-Crew
- Commit
238ae8c
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.