hackathon-sponsor-integrator

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a process for ingesting external documentation to generate code, which presents a surface for indirect prompt injection. This is a characteristic of the skill's intended functionality.
  • Ingestion points: The raw_documentation input in SKILL.md.
  • Boundary markers: No specific delimiters are used to wrap the untrusted documentation input.
  • Capability inventory: The skill generates setup commands and implementation code (bootstrap_code).
  • Sanitization: No explicit sanitization or filtering of the documentation content is performed before processing.
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to install standard developer tools and packages from official registries, such as @cartesi/cli and graphql-request. These are used appropriately within the context of technology integration.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 01:03 PM
Security Audit — agent-trust-hub — hackathon-sponsor-integrator