Run a Hermes agent task whenever files appear, change, or disappear in a folder, using AutoRAG's file automations plus Hermes cron. Use when the user wants something done automatically for new files ("when a PDF lands in Downloads, summarize it and message me"), or wants to list or remove such an automation. Not for one-off questions about files (use the search skill) and not for first-time setup of the index (use the setup skill).
92%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Medium
Suggest reviewing before use
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
The skill has the agent register a persistent daemon via launchd or systemd `--user` (surviving logout), and generate scripts and cron jobs, which is a machine-state change close to the flagged service-file category, though it uses user-level scope and no sudo.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow reads file paths from a watched local folder (for example Downloads) and passes them as free-text prompt data to the agent. An outsider can cause a file with an attacker-chosen name to land there, such as through an email attachment or web download, without the agent selecting it.
Marker-Inc-Korea/AutoRAG
399c591
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.