coda-ai
Warn
Audited by Snyk on Mar 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly documents commands (coda-ai docs/pages/read) that fetch and return Coda.io documents and page content (user-generated third-party content) which the agent is expected to read and could contain untrusted instructions that influence subsequent actions.
Audit Metadata