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