skills/lovstudio/cc-mv/lov-cc-mv/Gen Agent Trust Hub

lov-cc-mv

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx -y @lovstudio/cc-mv and npx -y @lovstudio/cc-migrate-session to download and run code from the NPM registry. These resources are owned by the skill author.
  • [COMMAND_EXECUTION]: The skill executes shell commands to perform directory moves, read session lists, and update internal configuration files in the ~/.claude directory.
  • [PROMPT_INJECTION]: The skill evaluates untrusted data from Claude Code's session history (e.g., firstUserPrompt) to summarize or filter sessions for the user. While this creates a surface where malicious session content could influence the agent, the risk is inherent to the task of managing chat history.
  • Ingestion points: Reads session metadata from the JSON output of the CLI tool in SKILL.md.
  • Boundary markers: None identified in the instructions for displaying or processing session data.
  • Capability inventory: Includes filesystem directory moves and modifications to the user's Claude Code state files.
  • Sanitization: The skill does not specify sanitization or escaping for the session content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 07:38 AM
Security Audit — agent-trust-hub — lov-cc-mv