book-study

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it incorporates external, untrusted content into its long-term knowledge base.
  • Ingestion points: Data enters the agent's context through user-provided notes, verbal summaries, and local file paths (PDF, TXT, MD) as defined in the 'Phase 2: Read + Compile (Ingest)' section of SKILL.md.
  • Boundary markers: The skill instructions do not provide delimiters or specific guidance to the agent to disregard instructions that might be embedded within the ingested books or user notes.
  • Capability inventory: The skill performs file reads (ingesting external documents), file writes (creating and updating the 'book-wiki/'), and high-level knowledge synthesis (summarizing and querying concepts).
  • Sanitization: There is no evidence of content validation, escaping, or filtering of the external data before it is stored in the wiki or used in subsequent Socratic questioning phases.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 05:40 AM