skills/broomva/skills/braindump/Gen Agent Trust Hub

braindump

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns detected. The skill is designed to organize user-provided text into a local Obsidian vault.
  • [PROMPT_INJECTION]: The skill processes untrusted input (transcripts and raw text) which could contain indirect prompt injections.
  • Ingestion points: Raw user text and voice transcripts processed in SKILL.md.
  • Boundary markers: No explicit markers or ignore instructions warnings used to wrap the input.
  • Capability inventory: Creates and updates markdown files in ~/broomva-vault/ (SKILL.md).
  • Sanitization: The skill does not specify sanitization or escaping of the input data before processing or filing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 03:32 PM
Security Audit — agent-trust-hub — braindump