The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through untrusted configuration files located in the directories it processes.
Ingestion points: The script scripts/organize.py reads config.json (line 19) and .organize_log.json (line 82) from the user-specified directory.
Boundary markers: Absent. There are no mechanisms to verify that the configuration files were created by the user or to ignore instructions embedded within the data.
Capability inventory: The script possesses file system modification capabilities, specifically moving files (rename on lines 64 and 91) and creating directories (mkdir on lines 62 and 90).
Sanitization: Absent. The script does not validate the target_name retrieved from the rules section of config.json, allowing potential path traversal attacks (e.g., using .. to move files outside of the intended target directory).

file-organizer