google-agents-cli-eval

Fail

Audited by Snyk on Nov 17, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate evaluation guide, but its mock-mode snippet returns fabricated "success" data when no real API key is present, which can hide a limitation from the user and make evals look passing.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (low risk: 0.10). The required eval workflow reads locally generated results and traces, which can include web content that the evaluated agent fetched through google_search or load_web_page, so outsider text reaches the LLM only after the agent under test retrieves it.

Issues (2)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 17, 2026, 08:49 PM
Issues
2