the-call-booker

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security threats or malicious patterns were detected. The skill focuses on copywriting assistance and calendar scheduling logic.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided conversation history to generate personalized message drafts. While this is an ingestion point for external data, the skill lacks execution tools (like file system access or network calls), limiting the impact to the generated text content.
  • Ingestion points: SKILL.md (via user input 'The conversation so far').
  • Boundary markers: Absent.
  • Capability inventory: No subprocess calls, network operations, or file system modifications are present.
  • Sanitization: Not explicitly defined.
  • [DATA_EXPOSURE]: The skill references a local configuration file (.agents/product-context.md) to align with brand voice and banned words. This is a standard practice for maintaining consistency and does not expose sensitive system or user data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 12:03 PM