skills/promovaweb/mvpfy/mvpfy-setup/Gen Agent Trust Hub

mvpfy-setup

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill executes npx --yes @promovaweb/mvpfy install, which downloads and runs an installation package from the vendor's repository.
  • [COMMAND_EXECUTION]: The instructions command the execution of shell tools including mvpfy doctor, mvpfy progress, and mvpfy update to verify and manage the project environment.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8).
  • Ingestion points: Reads existing instructions and the MVP.md file from the consumer project root (SKILL.md).
  • Boundary markers: No delimiters or 'ignore embedded instructions' warnings are present when reading external project data.
  • Capability inventory: The skill has the capability to execute shell commands (npx, mvpfy) which could be abused if malicious instructions are present in the project files.
  • Sanitization: There is no evidence of validation or filtering for the content ingested from the project's local files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 09:24 PM
Security Audit — agent-trust-hub — mvpfy-setup