moai-essentials-refactor
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a legitimate utility for source code transformation and architectural review. A complete audit of the instructions, metadata, and code snippets in SKILL.md and supporting files reveals no evidence of prompt injection, data exfiltration, or unauthorized privilege escalation.- [PROMPT_INJECTION]: A potential vulnerability surface for indirect prompt injection exists because the skill is designed to ingest and process local source code which could contain adversarial content. However, no active exploitation logic was found.
- Ingestion points: Reads local project files using the 'Read' tool and the 'rope' library as defined in SKILL.md.
- Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the code being processed.
- Capability inventory: The skill leverages 'Bash', 'Edit', and 'mcp__context7' tools to perform analysis and apply transformations.
- Sanitization: No specific sanitization or filtering of the code content is present in the provided templates.
Audit Metadata