ai-assessment-scale

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: 1.00). The SKILL.md explicitly requires reviewing a project_url_or_codebase and "Gather evidence" by inspecting commit history, README, and repository files (Step 1 / Inputs Required), which means the agent will fetch and interpret user-generated, public repository content that can directly influence assessment decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 10:44 PM