skills/mrvladd-d/memobank/mb-verify/Gen Agent Trust Hub

mb-verify

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: No security issues detected. The skill consists of markdown instructions that define a standard verification process for an AI agent. It uses local files for context and suggests routine verification tools.
  • [COMMAND_EXECUTION]: The skill instructs the agent to run CLI commands and tests for verification. This is the primary purpose of the skill and occurs within the project's local environment.
  • [PROMPT_INJECTION]: The skill is subject to an indirect prompt injection surface as it ingests task requirements from local files. Ingestion points: .memory-bank/ and .protocols/ files. Boundary markers: Absent. Capability inventory: CLI execution and browser automation. Sanitization: Absent. The risk is considered safe as it is inherent to processing task data within a trusted local project.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 05:50 AM