starknet-react-rules

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to analyze and modify files matching the 'starknet/**/*.tsx' glob. While this creates a surface for indirect prompt injection from untrusted source code, the skill does not have elevated privileges or network capabilities that would facilitate a high-risk exploit. Ingestion occurs via the Read tool, and no specific sanitization logic is defined in the prompt instructions.
  • [COMMAND_EXECUTION]: The 'Memory Protocol' in the SKILL.md file instructs the agent to use a shell command ('cat .claude/context/memory/learnings.md') to maintain state. This is a common pattern for agentic memory management and targets a local, non-sensitive directory specifically used for agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 07:52 AM