mcporter
Warn
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The 'mcporter' CLI provides a '--stdio' option (e.g., 'mcporter call --stdio "bun run ./server.ts"') that allows the agent to execute arbitrary shell commands and scripts on the host system.
- [EXTERNAL_DOWNLOADS]: The skill metadata triggers the installation of the 'mcporter' Node.js package from the public registry.
- [REMOTE_CODE_EXECUTION]: The 'mcporter generate-cli --command ' functionality allows fetching and processing of logic from remote endpoints, which could facilitate code execution from untrusted sources.
- [DATA_EXFILTRATION]: The skill provides an indirect prompt injection surface by ingesting data from external MCP servers. 1. Ingestion points: Output from 'mcporter call' in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Command execution via '--stdio' and network operations via 'call' in SKILL.md. 4. Sanitization: Absent. Additionally, the tool manages sensitive credentials via 'mcporter auth' and 'mcporter config', which could be exposed via network calls to untrusted servers.
Audit Metadata