lov-cc-mv
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill executes external code via the command
npx -y @lovstudio/cc-mv. This downloads and runs a package from the npm registry managed by the vendor, lovstudio. - [COMMAND_EXECUTION]: The skill invokes shell commands such as
mvfor filesystem operations andnpxfor executing the migration utility. - [EXTERNAL_DOWNLOADS]: The skill fetches the
@lovstudio/cc-mvCLI tool from the npm registry during the migration process. - [DATA_EXFILTRATION]: The skill accesses sensitive Claude Code data in
~/.claude/projects/,~/.claude/history.jsonl, and~/.claude/sessions/. This access is necessary for migration but involves processing private conversation logs and prompt history. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted chat history which could contain malicious instructions. * Ingestion points: Reads
.jsonlsession history files from the Claude Code projects directory. * Boundary markers: None; the agent is instructed to summarize raw chat content to identify session topics. * Capability inventory: The skill possesses command execution (npx,mv) and filesystem write capabilities for sensitive configuration folders. * Sanitization: No specific filtering or sanitization of prompt content is mentioned before it is parsed by the agent.
Audit Metadata