pdf-explore

Pass

Audited by Gen Agent Trust Hub on Sep 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external PDF files, which are untrusted sources.
  • Ingestion points: Processes the "full PDF", including abstract, methods, figures, and supplements as described in SKILL.md.
  • Boundary markers: No explicit instructions are provided to the agent to treat content within the PDFs as untrusted or to ignore embedded instructions.
  • Capability inventory: The skill describes capabilities to parse files and "Save extracted notes, annotations, and provenance as artifacts," indicating file writing capabilities.
  • Sanitization: There are no mentions of sanitizing or validating the content extracted from the PDFs before processing or saving it.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 27, 2026, 03:23 AM