whetstone
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is designed to ingest external content (original text and annotations) which it then summarizes and reformats. This creates a standard attack surface for indirect prompt injection, where malicious instructions embedded in the source text could attempt to influence the agent's summary or behavior.
- Ingestion points:
SKILL.mdStep 1 (Accepts original text, links, and user annotations). - Boundary markers: Absent; the skill relies on natural language parsing to distinguish content.
- Capability inventory: Text generation and summarization only; no file writes, network requests, or code execution capabilities are present in the skill definition.
- Sanitization: Includes basic filename character replacement (converting ASCII quotes to brackets) to ensure Windows compatibility.
Audit Metadata