observability
Warn
Audited by Snyk on Mar 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). Yes — the skill explicitly fetches and ingests Sentry issue payloads and Seer webhook events from third-party Sentry APIs/webhooks (e.g., the GitHub Action curl to "https://sentry.io/api/0/issues/$ISSUE_ID/" and piping issue.json to Claude, plus Sentry webhook handlers) and instructs the agent to analyze and act on that untrusted, user-generated content, which could enable indirect prompt injection.
Audit Metadata