skills/kriscard/skills/process-inbox/Gen Agent Trust Hub

process-inbox

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local obsidian CLI commands (files, read, move, delete) to manage notes within the user's specific `0
  • Inbox/ folder.- **[PROMPT_INJECTION]:** The skill is subject to indirect prompt injection because it reads and processes the content of untrusted files from the inbox. This risk is mitigated by the mandatory human-in-the-loop confirmation step (AskUserQuestion`) required for all destructive or organizational actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 06:36 PM
Security Audit — agent-trust-hub — process-inbox