writing-study-cards

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely instructional and does not include any executable code, network operations, or attempts to access sensitive system files.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it is designed to ingest and process untrusted user-provided content such as articles and notes. However, the instructions focus on structural quality and do not attempt to override safety guardrails. \n
  • Ingestion points: User-provided topics, notes, or articles mentioned in the SKILL.md description. \n
  • Boundary markers: None specified in the instructions. \n
  • Capability inventory: Interacts with the create_card and import_card_hierarchy tools as specified in the workflow. \n
  • Sanitization: No explicit sanitization or validation logic is provided for the external content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 05:00 AM
Security Audit — agent-trust-hub — writing-study-cards