outlook-automation
Warn
Audited by Snyk on Apr 3, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly reads user-generated, potentially untrusted email and calendar content from the local Outlook session (e.g., SKILL.md and reference/cli.md show commands like
uv run ... get --include-body,list --include-body-snippet, andcalendar get --include-body) and those bodies can be used to create drafts/replies or drive actions, so third-party content can materially influence behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata