The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses standard shell utilities such as find, mv, rm, jq, and gzip to analyze file sizes, move files to the system trash, delete confirmed items, and verify the integrity of remaining JSON files.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits a potential attack surface by processing file names and metadata from the local filesystem, which could be manipulated to influence agent behavior, though the risk is mitigated by the structured workflow and confirmation steps.
Ingestion points: File names and attributes retrieved through find . commands in SKILL.md.
Boundary markers: The instructions do not specify the use of delimiters or boundary markers when handling the list of files to be processed.
Capability inventory: The skill has access to file deletion (rm), relocation (mv), compression (gzip), and parsing commands (jq) as documented in SKILL.md.
Sanitization: There are no explicit requirements for sanitizing or escaping file paths before they are passed to shell commands.

cleaning-up-research-sessions