Daily Focus Planner

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data retrieved from external CRM and task management systems through the execute_action capability. This creates a potential surface for indirect prompt injection if malicious instructions are embedded within deal names, contact notes, or task descriptions.
  • Ingestion points: Data is ingested from pipeline_deals, contacts_needing_attention, and open_tasks via platform tool calls.
  • Boundary markers: The skill definition does not explicitly define delimiters (e.g., XML tags or triple quotes) to isolate ingested data from the instruction logic.
  • Capability inventory: The skill is restricted to reading from CRM/Tasks and generating structured output. It lacks high-risk capabilities like arbitrary command execution, file system writes, or outbound network requests.
  • Sanitization: No explicit sanitization or filtering of the ingested content is described in the skill logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 11:37 AM