anki-card-maker

Pass

Audited by Gen Agent Trust Hub on Nov 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided study materials (Markdown, text, notes) to generate flashcards. This creates a surface for indirect prompt injection where malicious instructions embedded in the study material could attempt to influence the agent's behavior during the extraction process.
  • Ingestion points: User-provided study material files as described in the workflow in SKILL.md and processed by the script.
  • Boundary markers: Absent; the skill does not use delimiters or ignore-instructions to isolate untrusted content from the agent's task context.
  • Capability inventory: The skill performs file read and write operations via the generate_flashcards.py script and can process potentially large amounts of user-supplied data.
  • Sanitization: Absent; the script provides basic formatting (e.g., converting bold Markdown to HTML) but lacks sanitization or validation mechanisms to prevent the interpretation of instructions contained within the input text.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 22, 2026, 01:12 AM