coral
Warn
Audited by Snyk on May 14, 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's SKILL.md explicitly instructs the agent to query connected third-party sources (e.g., GitHub, Slack, Linear, Datadog, Sentry) and to read per-table "guide" content and coral.inputs (steps 2 and 5), so the agent will ingest untrusted/user-generated content from those external sources that can materially influence query construction and subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata