The Agent Skills Directory

[DATA_EXFILTRATION]: The skill reads API tokens from a local configuration file at ~/.lytics/accounts.toml. This is the intended and documented method for managing access to the Lytics accounts being synchronized. Data is transmitted only to the official Lytics API endpoint (https://api.lytics.io), which is a well-known service and belongs to the vendor. No unauthorized exfiltration or exposure of sensitive data to third parties was detected.
[COMMAND_EXECUTION]: The skill uses curl to perform API operations. These commands are constructed using tokens and URLs resolved from the local configuration file or user input. The execution is scoped to the Lytics API and is necessary for the skill's synchronization functionality.
[SAFE]: No evidence of prompt injection, obfuscation, remote code execution, or persistence mechanisms was found. The skill implements safety layers including dry-run modes, confirmation gates for bulk operations, and read-after-write verification to ensure data integrity.

account-sync