The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes a local script scripts/handoff.sh to initialize the handoff document. Technical review of the script confirms it implements secure file-handling practices, such as using mktemp for atomic writes and checking for file existence to prevent accidental overwrites.
[DATA_EXPOSURE]: No sensitive file access or credential harvesting was identified. The skill only interacts with files explicitly provided by the user or the default HANDOFF.md to store documentation.
[REMOTE_CODE_EXECUTION]: The skill does not perform any external downloads or execute remote scripts. It relies entirely on the included local bash script and the agent's internal reasoning.
[SAFE]: No obfuscation, malicious prompt injection patterns, or persistence mechanisms were detected. The skill's operations are transparent and strictly limited to its documented purpose of generating status and transition notes.

handoff