managing-reminders
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a standard surface for processing user-generated content by taking natural language requests and mapping them to tool parameters like 'title'. * Ingestion points: Natural language user input (e.g., 'remind me to...') is used to construct the reminder title and message in SKILL.md. * Boundary markers: No explicit delimiter or instructions to ignore embedded commands are specified in the prompt logic. * Capability inventory: The agent uses tools like reminder-create, reminder-update, and reminders-list which interact with the PostHog API. * Sanitization: There are no instructions for sanitizing or escaping the user-provided title string before passing it to the tool call.
- [SAFE]: The skill uses vendor-specific tools and established infrastructure (posthog.com) to facilitate intended user functionality for task management and internal project notifications.
Audit Metadata