The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes standard Unix utilities such as stat, ls, du, wc, find, grep, xargs, sort, and head to gather file statistics and metadata. These commands are configured for read-only, non-destructive operations.
[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external file content through the Read tool and grep operations. This creates a surface where the agent could potentially process malicious instructions embedded within the files being analyzed, though the skill itself does not contain malicious intent.
[SAFE]: The skill does not perform network operations, exfiltrate data, attempt privilege escalation, or use any form of obfuscation. All proposed commands are consistent with the stated purpose of file analysis and metadata retrieval.

file-operations