affinda

Warn

Audited by Snyk on Mar 4, 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.md explicitly exposes fetching and reading Affinda resources (e.g., "get-document", "list-documents", and the "membrane request" proxy) which will retrieve user-uploaded, untrusted third-party content (resumes/documents) that the agent is expected to read and could materially influence subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 08:55 AM