moai-project-template-optimizer

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses local shell commands including ls, grep, find, and tar to analyze and manage backups within the .moai-backups/ directory. These operations are restricted to the local filesystem and serve the skill's primary purpose of backup discovery and inspection.
  • [EXTERNAL_DOWNLOADS]: The skill is configured to use WebFetch and the Context7 MCP integration (mcp__context7__get-library-docs) to retrieve documentation and library information during the optimization workflow.
  • [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface when reading and merging project backups and configuration files. 1. Ingestion points: Data is ingested from files in .moai-backups/, .claude/settings.json, and CLAUDE.md. 2. Boundary markers: No explicit markers or instructions to ignore embedded prompts are provided in the described smart merge logic. 3. Capability inventory: The skill has tools for file system access, command execution, and web requests (WebFetch, WebSearch). 4. Sanitization: No content validation or sanitization routines are defined for the data extracted from user customizations or backups before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:07 AM