weekly-review
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from external sources, specifically connected note-taking applications.
- Ingestion points: The instructions specify that the agent can read the week's daily notes, meeting notes, and project notes from a connected app (e.g., Step 1 in 'How to do it').
- Boundary markers: The skill suggests marking extracted items with their source (e.g., '(from 2026-10-21 daily note)'), but it does not implement formal delimiters or safety instructions to prevent the agent from obeying commands embedded within those notes.
- Capability inventory: The skill's capabilities are limited to reading text, summarizing it, and offering to save the final review note. It does not possess capabilities for arbitrary command execution or external network exfiltration of sensitive data.
- Sanitization: There is no explicit sanitization of the content retrieved from the notes app before processing.
Audit Metadata