skills/momhq/mom/mom-rebuild/Gen Agent Trust Hub

mom-rebuild

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the MOM CLI tool via Homebrew (brew install momhq/tap/mom). This resource is provided by the skill's author (momhq) and the instruction requires explicit user consent before execution.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute administrative commands including mom vault rebuild, mom vault status, and command -v mom. These commands are used as intended for checking prerequisites and performing the vault restoration.
  • [PROMPT_INJECTION]: The skill processes 'full captured history' to regenerate the vault. This data ingestion constitutes a surface for indirect prompt injection, where malicious content previously captured in the history could attempt to influence the LLM synthesis engine during the rebuild process.
  • Ingestion points: Processes captured history data during the mom vault rebuild operation.
  • Boundary markers: None identified in the provided instructions.
  • Capability inventory: Execution of shell commands via Bash tool (SKILL.md).
  • Sanitization: The skill relies on the underlying mom CLI for processing, and no explicit sanitization or escaping of the history data is mentioned in the prompt instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 03:50 PM
Security Audit — agent-trust-hub — mom-rebuild