skills/mhliulgy/my-skills/eda-vm/Gen Agent Trust Hub

eda-vm

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides templates and protocols for executing arbitrary shell commands and scripts on a remote Linux host (vm) via SSH.
  • [DATA_EXFILTRATION]: Instructions include the bidirectional transfer of local project files and remote tool outputs using the SCP protocol, identifying the specific requirement for the -O flag for legacy compatibility.
  • [INDIRECT_PROMPT_INJECTION]: As the skill is designed to ingest and process external project source code (Verilog, SystemVerilog) and simulation logs from third-party tools, it presents an attack surface for indirect prompt injection if those files contain malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 05:08 PM
Security Audit — agent-trust-hub — eda-vm