The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes standard filesystem utilities including ls, find, du, mkdir, and mv to analyze and reorganize files within specified directories. These commands are localized to the user's environment and are essential to the skill's primary function.\n- [PROMPT_INJECTION]: Instructions explicitly direct the agent to ask clarifying questions and obtain user consent before deleting duplicates or moving files, which serves as a safeguard against accidental data loss.\n- [PROMPT_INJECTION]: There is an attack surface for indirect prompt injection because the skill ingests untrusted data from the filesystem (filenames and metadata) and incorporates it into the agent's context. 1. Ingestion points: Results from ls, find, and file commands. 2. Boundary markers: None present in the instructions. 3. Capability inventory: Commands for moving (mv), creating directories (mkdir), and deleting files. 4. Sanitization: No sanitization or validation of the ingested filesystem data is described.\n- [SAFE]: No evidence of malicious behavior, such as credential theft, network-based data exfiltration, privilege escalation, or code obfuscation, was found in the skill content.

file-organizer