c-briefing
Warn
Audited by Snyk on Mar 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly instructs the briefing to "pull from" installed skills like c-email, c-slack, and c-github ( unread emails, Slack mentions, and PRs ), which are untrusted/user-generated third‑party sources the agent reads and uses to prioritize/flag items.
Audit Metadata