The Agent Skills Directory

[SAFE]: No security threats or malicious patterns were identified in the skill's instructions, metadata, or scripts.
[COMMAND_EXECUTION]: The skill utilizes a local script scripts/meeting_prep_briefer.py to format briefing documents. Technical review confirms the script is limited to parsing JSON and printing text to the console using standard Python libraries, with no network access or dangerous system-level operations.
[INDIRECT_PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection as it processes external data from assets/meeting_input.json.
Ingestion points: The file assets/meeting_input.json is read by the meeting_prep_briefer.py script.
Boundary markers: None identified in the skill instructions to delimit untrusted content.
Capability inventory: The skill is limited to local text formatting and stdout printing; no file-writing, network, or high-privilege capabilities are present.
Sanitization: The input is parsed as JSON, but the resulting strings are not sanitized before being formatted into the markdown briefing.

calendar-prep