axiom-ai

Warn

Audited by Snyk on May 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: 0.90). The skill's Tool protocol and examples (e.g., GetFactTool / GetWeatherTool and the "Tool Calling Flow" in skills/foundation-models.md and foundation-models-ref.md) explicitly instruct creating tools that fetch data from external/public APIs (Wikipedia, news APIs, "any custom API") whose outputs are inserted into the session transcript and autonomously consumed by the model, enabling untrusted third‑party content to influence subsequent decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 11, 2026, 01:17 PM
Issues
1