airbyte-agent

Warn

Audited by Snyk on May 15, 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). The skill explicitly drives connectors to read data from third-party SaaS sources (e.g., "HubSpot, Salesforce, Slack, GitHub" in SKILL.md) and requires the agent to run connectors describe / connectors execute (references/connectors-describe.md and references/connectors-execute.md) and interpret returned entity data as part of its workflow, which exposes it to untrusted/user-generated content that can influence subsequent tool use.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 15, 2026, 12:48 AM
Issues
1
Security Audit — snyk — airbyte-agent