weekly-review-planning

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests data from external sources such as Google Workspace (calendars), Obsidian, Notion (notes), and email triage systems, which creates an attack surface for indirect prompt injection.
  • Ingestion points: SKILL.md (Procedure steps 2 and 3).
  • Boundary markers: The instructions do not define specific delimiters for separating data from instructions, but they do enforce a verification step.
  • Capability inventory: The skill interacts with related skills to read and write to calendars, notes, and task management systems.
  • Sanitization: No explicit sanitization or filtering of external content is described.
  • Mitigation: The skill employs significant safety guardrails by mandating that the agent must not mutate data without approval (Step 3 and 7) and must verify all writes against the approved summary (Step 7).
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 07:40 AM
Security Audit — agent-trust-hub — weekly-review-planning