Skills
skills/wadewarren/gws-claude-plugin/recipe-plan-weekly-schedule/Gen Agent Trust Hub

recipe-plan-weekly-schedule

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the gws command-line tool to interact with Google Calendar, including querying the agenda, checking free/busy status, and inserting new events. These operations are restricted to calendar management.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted data from external calendar entries.
  • Ingestion points: The agent reads external data using gws calendar +agenda and gws calendar freebusy query as defined in SKILL.md.
  • Boundary markers: None identified; calendar data is processed directly into the agent's context.
  • Capability inventory: The agent can perform write operations using gws calendar +insert as seen in SKILL.md.
  • Sanitization: There is no evidence of validation or sanitization of the content retrieved from the calendar service.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 04:56 PM