OverviewHistoryStatsSecurity
Security
Independent checks from skills.sh's audit partners.
Independent checks from skills.sh's audit partners.
Independent checks from skills.sh's audit partners.
Fail5 providerslatest audit Apr 15, 2026
Independent checks from skills.sh's audit partners.
This skill grants an AI agent broad access to highly sensitive Microsoft 365 data, including emails, Teams messages, and private documents. While intended for workplace intelligence, it creates a significant attack surface for indirect prompt injection; an attacker could send a malicious email or message that, when read by the agent through this skill, could hijack the agent's session or trick it into leaking information.
Detected behaviors
No alerts
No issues
1 file scanned · No issues
Score: 93/100 · 2 sections analyzed