skills/dojoengine/book/dojo-review/Gen Agent Trust Hub

dojo-review

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill is designed to analyze untrusted external data (user-provided Dojo code) using Read, Grep, and Glob tools.
  • Ingestion points: Source code files accessed via allowed tools.
  • Boundary markers: None identified in the provided skill definition to isolate code content from instructions.
  • Capability inventory: The skill lacks execution (exec/eval), file-write, or network capabilities, limiting the potential impact of an injection.
  • Sanitization: No logic is present to sanitize or filter potential malicious instructions embedded within the code being reviewed.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 02:36 AM