summarize

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs documented, transparent operations related to document summarization, file writing, and optional knowledge-base publishing.
  • [EXTERNAL_DOWNLOADS]: The skill references the pymupdf library for PDF processing. This is a widely recognized and trusted third-party package for text extraction.
  • [PROMPT_INJECTION]: The skill provides an interface for processing untrusted external documents (PDF/EPUB), which creates a surface for indirect prompt injection.
  • Ingestion points: The agent reads document content from pasted text or external files as specified in SKILL.md.
  • Boundary markers: No explicit delimiters are used to wrap the ingested content or protect the summary instructions from potential embedded commands.
  • Capability inventory: The skill uses file-writing capabilities to create .md summaries, can execute the extract_pdf_pages.py script, and optionally publishes content to integrated platforms like Notion.
  • Sanitization: No validation or escaping is applied to the content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 05:09 AM
Security Audit — agent-trust-hub — summarize